aiskillstore/marketplace / skills/abdullahmalik17/browser-use
browser-use
VerifiedBrowser automation using Playwright MCP. Navigate websites, fill forms, click elements, take screenshots, and extract data. Use when tasks require web browsing, form submission, web scraping, UI testing, or any browser interaction.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.2 KB |
| references/playwright-tools.md | markdown | 19.8 KB |
| scripts/mcp-client.py | script | 16.4 KB |
| scripts/start-server.sh | script | 670 B |
| scripts/stop-server.sh | script | 898 B |
| skill-report.json | config | 109.6 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-07T18:25:44.347Z",
"slug": "abdullahmalik17-browser-use",
"source_url": "https://github.com/AbdullahMalik17/Cloud-Native-AI/tree/main/.claude/skills/browser-use",
"source_ref": "main",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "145c8eff8d221f739aafffcb5e49e85150536499aa3b71b985c42e59df508c64",
"tree_hash": "29fbc702fe5342c5bb5441f0b80719bfc5f82c9105190fc307c8521402ee5047",
"provenance": {
"model_effective": "codex",
"fallback_chain": [
{
"agent": "codex",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "browser-use",
"description": "Automate browser workflows with Playwright MCP. Navigate pages, fill forms, click elements, take screenshots, and extract page data through MCP tools.",
"summary": "Use Playwright MCP to control a browser from Claude, Codex, or Claude Code.",
"icon": "📦",
"version": "1.0.1",
"author": "AbdullahMalik17",
"license": "MIT",
"tags": [
"browser-automation",
"playwright",
"mcp",
"web-testing",
"scraping"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"external_commands",
"network",
"filesystem"
],
"category": "devops"
},
"security_audit": {
"risk_level": "high",
"is_blocked": false,
"safe_to_publish": false,
"analysis_status": "ok",
"summary": "Most static hits in the generated reference documentation are false positives from Markdown backticks and JSON Schema URLs. Confirmed risks remain in the stdio subprocess path, shell lifecycle helpers, HTTP-capable MCP client requests, predictable /tmp PID files, and browser JavaScript execution guidance. No prompt injection text was found in the reviewed files.",
"remediation": [
{
"issue": "Unrestricted stdio command execution",
"suggestion": "Replace subprocess.Popen with shell=False argv execution, or allow only known MCP server commands.",
"severity": "high"
},
{
"issue": "Unpinned Playwright MCP package",
"suggestion": "Avoid @latest in npx examples and scripts. Pin a reviewed package version.",
"severity": "medium"
},
{
"issue": "Predictable PID files in /tmp",
"suggestion": "Store PID files in a user-owned runtime directory and validate ownership and numeric PID content.",
"severity": "medium"
},
{
"issue": "Shared browser session state",
"suggestion": "Warn users before authenticated browsing and clear browser state after sensitive workflows.",
"severity": "medium"
},
{
"issue": "Powerful browser code execution tools",
"suggestion": "Prefer named MCP tools and require explicit approval before browser_evaluate or browser_run_code on sensitive pages.",
"severity": "high"
}
],
"risk_factor_evidence": [
{
"factor": "external_commands",
"evidence": [
{
"file": "references/playwright-tools.md",
"line_start": 247,
"line_end": 247
},
{
"file": "references/playwright-tools.md",
"line_start": 308,
"line_end": 308
},
{
"file": "references/playwright-tools.md",
"line_start": 471,
"line_end": 480
},
{
"file": "references/playwright-tools.md",
"line_start": 515,
"line_end": 533
},
{
"file": "scripts/mcp-client.py",
"line_start": 191,
"line_end": 191
},
{
"file": "scripts/mcp-client.py",
"line_start": 204,
"line_end": 204
},
{
"file": "scripts/mcp-client.py",
"line_start": 348,
"line_end": 348
},
{
"file": "scripts/mcp-client.py",
"line_start": 371,
"line_end": 371
},
{
"file": "scripts/mcp-client.py",
"line_start": 377,
"line_end": 379
},
{
"file": "scripts/start-server.sh",
"line_start": 9,
"line_end": 9
},
{
"file": "scripts/start-server.sh",
"line_start": 10,
"line_end": 10
},
{
"file": "scripts/start-server.sh",
"line_start": 20,
"line_end": 20
},
{
"file": "scripts/start-server.sh",
"line_start": 21,
"line_end": 21
},
{
"file": "scripts/start-server.sh",
"line_start": 1,
"line_end": 1
},
{
"file": "scripts/stop-server.sh",
"line_start": 9,
"line_end": 9
},
{
"file": "scripts/stop-server.sh",
"line_start": 12,
"line_end": 12
},
{
"file": "scripts/stop-server.sh",
"line_start": 1,
"line_end": 1
},
{
"file": "SKILL.md",
"line_start": 13,
"line_end": 19
},
{
"file": "SKILL.md",
"line_start": 19,
"line_end": 22
},
{
"file": "SKILL.md",
"line_start": 22,
"line_end": 29
},
{
"file": "SKILL.md",
"line_start": 29,
"line_end": 36
},
{
"file": "SKILL.md",
"line_start": 36,
"line_end": 42
},
{
"file": "SKILL.md",
"line_start": 42,
"line_end": 49
},
{
"file": "SKILL.md",
"line_start": 49,
"line_end": 53
},
{
"file": "SKILL.md",
"line_start": 53,
"line_end": 60
},
{
"file": "SKILL.md",
"line_start": 60,
"line_end": 64
},
{
"file": "SKILL.md",
"line_start": 64,
"line_end": 66
},
{
"file": "SKILL.md",
"line_start": 66,
"line_end": 82
},
{
"file": "SKILL.md",
"line_start": 82,
"line_end": 86
},
{
"file": "SKILL.md",
"line_start": 86,
"line_end": 94
},
{
"file": "SKILL.md",
"line_start": 94,
"line_end": 98
},
{
"file": "SKILL.md",
"line_start": 98,
"line_end": 101
},
{
"file": "SKILL.md",
"line_start": 101,
"line_end": 105
},
{
"file": "SKILL.md",
"line_start": 105,
"line_end": 107
},
{
"file": "SKILL.md",
"line_start": 107,
"line_end": 110
},
{
"file": "SKILL.md",
"line_start": 110,
"line_end": 112
},
{
"file": "SKILL.md",
"line_start": 112,
"line_end": 140
}
]
},
{
"factor": "network",
"evidence": [
{
"file": "references/playwright-tools.md",
"line_start": 19,
"line_end": 19
},
{
"file": "references/playwright-tools.md",
"line_start": 56,
"line_end": 56
},
{
"file": "references/playwright-tools.md",
"line_start": 91,
"line_end": 91
},
{
"file": "references/playwright-tools.md",
"line_start": 127,
"line_end": 127
},
{
"file": "references/playwright-tools.md",
"line_start": 168,
"line_end": 168
},
{
"file": "references/playwright-tools.md",
"line_start": 199,
"line_end": 199
},
{
"file": "references/playwright-tools.md",
"line_start": 265,
"line_end": 265
},
{
"file": "references/playwright-tools.md",
"line_start": 284,
"line_end": 284
},
{
"file": "references/playwright-tools.md",
"line_start": 315,
"line_end": 315
},
{
"file": "references/playwright-tools.md",
"line_start": 368,
"line_end": 368
},
{
"file": "references/playwright-tools.md",
"line_start": 399,
"line_end": 399
},
{
"file": "references/playwright-tools.md",
"line_start": 418,
"line_end": 418
},
{
"file": "references/playwright-tools.md",
"line_start": 447,
"line_end": 447
},
{
"file": "references/playwright-tools.md",
"line_start": 478,
"line_end": 478
},
{
"file": "references/playwright-tools.md",
"line_start": 531,
"line_end": 531
},
{
"file": "references/playwright-tools.md",
"line_start": 559,
"line_end": 559
},
{
"file": "references/playwright-tools.md",
"line_start": 626,
"line_end": 626
},
{
"file": "references/playwright-tools.md",
"line_start": 675,
"line_end": 675
},
{
"file": "references/playwright-tools.md",
"line_start": 712,
"line_end": 712
},
{
"file": "references/playwright-tools.md",
"line_start": 758,
"line_end": 758
},
{
"file": "references/playwright-tools.md",
"line_start": 800,
"line_end": 800
},
{
"file": "references/playwright-tools.md",
"line_start": 838,
"line_end": 838
},
{
"file": "scripts/mcp-client.py",
"line_start": 146,
"line_end": 146
},
{
"file": "scripts/mcp-client.py",
"line_start": 271,
"line_end": 271
},
{
"file": "scripts/mcp-client.py",
"line_start": 314,
"line_end": 314
},
{
"file": "scripts/mcp-client.py",
"line_start": 323,
"line_end": 323
},
{
"file": "scripts/mcp-client.py",
"line_start": 328,
"line_end": 328
},
{
"file": "scripts/mcp-client.py",
"line_start": 333,
"line_end": 333
},
{
"file": "scripts/mcp-client.py",
"line_start": 33,
"line_end": 33
},
{
"file": "scripts/mcp-client.py",
"line_start": 10,
"line_end": 10
},
{
"file": "scripts/mcp-client.py",
"line_start": 16,
"line_end": 16
},
{
"file": "scripts/mcp-client.py",
"line_start": 20,
"line_end": 20
},
{
"file": "scripts/mcp-client.py",
"line_start": 23,
"line_end": 23
},
{
"file": "scripts/stop-server.sh",
"line_start": 12,
"line_end": 12
},
{
"file": "SKILL.md",
"line_start": 27,
"line_end": 27
},
{
"file": "SKILL.md",
"line_start": 44,
"line_end": 44
},
{
"file": "SKILL.md",
"line_start": 45,
"line_end": 45
},
{
"file": "SKILL.md",
"line_start": 48,
"line_end": 48
},
{
"file": "SKILL.md",
"line_start": 55,
"line_end": 55
},
{
"file": "SKILL.md",
"line_start": 58,
"line_end": 58
},
{
"file": "SKILL.md",
"line_start": 68,
"line_end": 68
},
{
"file": "SKILL.md",
"line_start": 72,
"line_end": 72
},
{
"file": "SKILL.md",
"line_start": 76,
"line_end": 76
},
{
"file": "SKILL.md",
"line_start": 80,
"line_end": 80
},
{
"file": "SKILL.md",
"line_start": 88,
"line_end": 88
},
{
"file": "SKILL.md",
"line_start": 92,
"line_end": 92
},
{
"file": "SKILL.md",
"line_start": 99,
"line_end": 99
},
{
"file": "SKILL.md",
"line_start": 108,
"line_end": 108
},
{
"file": "SKILL.md",
"line_start": 109,
"line_end": 109
}
]
},
{
"factor": "filesystem",
"evidence": [
{
"file": "scripts/start-server.sh",
"line_start": 9,
"line_end": 9
},
{
"file": "scripts/start-server.sh",
"line_start": 20,
"line_end": 20
},
{
"file": "scripts/start-server.sh",
"line_start": 6,
"line_end": 6
},
{
"file": "scripts/stop-server.sh",
"line_start": 10,
"line_end": 10
},
{
"file": "scripts/stop-server.sh",
"line_start": 12,
"line_end": 12
},
{
"file": "scripts/stop-server.sh",
"line_start": 15,
"line_end": 15
},
{
"file": "scripts/stop-server.sh",
"line_start": 19,
"line_end": 19
},
{
"file": "scripts/stop-server.sh",
"line_start": 28,
"line_end": 28
},
{
"file": "scripts/stop-server.sh",
"line_start": 6,
"line_end": 6
}
]
}
],
"static_findings": [
{
"id": "external_commands:references/playwright-tools.md:247:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "references/playwright-tools.md",
"line_start": 247,
"line_end": 247,
"snippet": "\"description\": \"Value to fill in the field. If the field is a checkbox, the value should be `true` o"
},
{
"id": "external_commands:references/playwright-tools.md:308:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "references/playwright-tools.md",
"line_start": 308,
"line_end": 308,
"snippet": "\"description\": \"Name of the key to press or a character to generate, such as `ArrowLeft` or `a`\""
},
{
"id": "external_commands:references/playwright-tools.md:471:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "references/playwright-tools.md",
"line_start": 471,
"line_end": 480,
"snippet": "\"description\": \"A JavaScript function containing Playwright code to execute. It will be invoked with"
},
{
"id": "external_commands:references/playwright-tools.md:515:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "references/playwright-tools.md",
"line_start": 515,
"line_end": 533,
"snippet": "\"description\": \"File name to save the screenshot to. Defaults to `page-{timestamp}.{png|jpeg}` if no"
},
{
"id": "network:references/playwright-tools.md:19:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/playwright-tools.md",
"line_start": 19,
"line_end": 19,
"snippet": "\"$schema\": \"http://json-schema.org/draft-07/schema#\""
},
{
"id": "network:references/playwright-tools.md:56:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/playwright-tools.md",
"line_start": 56,
"line_end": 56,
"snippet": "\"$schema\": \"http://json-schema.org/draft-07/schema#\""
},
{
"id": "network:references/playwright-tools.md:91:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/playwright-tools.md",
"line_start": 91,
"line_end": 91,
"snippet": "\"$schema\": \"http://json-schema.org/draft-07/schema#\""
},
{
"id": "network:references/playwright-tools.md:127:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/playwright-tools.md",
"line_start": 127,
"line_end": 127,
"snippet": "\"$schema\": \"http://json-schema.org/draft-07/schema#\""
},
{
"id": "network:references/playwright-tools.md:168:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/playwright-tools.md",
"line_start": 168,
"line_end": 168,
"snippet": "\"$schema\": \"http://json-schema.org/draft-07/schema#\""
},
{
"id": "network:references/playwright-tools.md:199:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/playwright-tools.md",
"line_start": 199,
"line_end": 199,
"snippet": "\"$schema\": \"http://json-schema.org/draft-07/schema#\""
},
{
"id": "network:references/playwright-tools.md:265:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/playwright-tools.md",
"line_start": 265,
"line_end": 265,
"snippet": "\"$schema\": \"http://json-schema.org/draft-07/schema#\""
},
{
"id": "network:references/playwright-tools.md:284:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/playwright-tools.md",
"line_start": 284,
"line_end": 284,
"snippet": "\"$schema\": \"http://json-schema.org/draft-07/schema#\""
},
{
"id": "network:references/playwright-tools.md:315:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/playwright-tools.md",
"line_start": 315,
"line_end": 315,
"snippet": "\"$schema\": \"http://json-schema.org/draft-07/schema#\""
},
{
"id": "network:references/playwright-tools.md:368:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/playwright-tools.md",
"line_start": 368,
"line_end": 368,
"snippet": "\"$schema\": \"http://json-schema.org/draft-07/schema#\""
},
{
"id": "network:references/playwright-tools.md:399:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/playwright-tools.md",
"line_start": 399,
"line_end": 399,
"snippet": "\"$schema\": \"http://json-schema.org/draft-07/schema#\""
},
{
"id": "network:references/playwright-tools.md:418:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/playwright-tools.md",
"line_start": 418,
"line_end": 418,
"snippet": "\"$schema\": \"http://json-schema.org/draft-07/schema#\""
},
{
"id": "network:references/playwright-tools.md:447:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/playwright-tools.md",
"line_start": 447,
"line_end": 447,
"snippet": "\"$schema\": \"http://json-schema.org/draft-07/schema#\""
},
{
"id": "network:references/playwright-tools.md:478:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/playwright-tools.md",
"line_start": 478,
"line_end": 478,
"snippet": "\"$schema\": \"http://json-schema.org/draft-07/schema#\""
},
{
"id": "network:references/playwright-tools.md:531:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/playwright-tools.md",
"line_start": 531,
"line_end": 531,
"snippet": "\"$schema\": \"http://json-schema.org/draft-07/schema#\""
},
{
"id": "network:references/playwright-tools.md:559:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/playwright-tools.md",
"line_start": 559,
"line_end": 559,
"snippet": "\"$schema\": \"http://json-schema.org/draft-07/schema#\""
},
{
"id": "network:references/playwright-tools.md:626:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/playwright-tools.md",
"line_start": 626,
"line_end": 626,
"snippet": "\"$schema\": \"http://json-schema.org/draft-07/schema#\""
},
{
"id": "network:references/playwright-tools.md:675:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/playwright-tools.md",
"line_start": 675,
"line_end": 675,
"snippet": "\"$schema\": \"http://json-schema.org/draft-07/schema#\""
},
{
"id": "network:references/playwright-tools.md:712:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/playwright-tools.md",
"line_start": 712,
"line_end": 712,
"snippet": "\"$schema\": \"http://json-schema.org/draft-07/schema#\""
},
{
"id": "network:references/playwright-tools.md:758:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/playwright-tools.md",
"line_start": 758,
"line_end": 758,
"snippet": "\"$schema\": \"http://json-schema.org/draft-07/schema#\""
},
{
"id": "network:references/playwright-tools.md:800:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/playwright-tools.md",
"line_start": 800,
"line_end": 800,
"snippet": "\"$schema\": \"http://json-schema.org/draft-07/schema#\""
},
{
"id": "network:references/playwright-tools.md:838:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/playwright-tools.md",
"line_start": 838,
"line_end": 838,
"snippet": "\"$schema\": \"http://json-schema.org/draft-07/schema#\""
},
{
"id": "external_commands:scripts/mcp-client.py:191:python-subprocess-popen",
"category": "external_commands",
"severity": "high",
"pattern": "Python subprocess.Popen",
"file": "scripts/mcp-client.py",
"line_start": 191,
"line_end": 191,
"snippet": "self._process: Optional[subprocess.Popen] = None"
},
{
"id": "external_commands:scripts/mcp-client.py:204:python-subprocess-popen",
"category": "external_commands",
"severity": "high",
"pattern": "Python subprocess.Popen",
"file": "scripts/mcp-client.py",
"line_start": 204,
"line_end": 204,
"snippet": "self._process = subprocess.Popen("
},
{
"id": "external_commands:scripts/mcp-client.py:348:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "scripts/mcp-client.py",
"line_start": 348,
"line_end": 348,
"snippet": "lines.append(f\"## `{name}`\\n\")"
},
{
"id": "external_commands:scripts/mcp-client.py:371:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "scripts/mcp-client.py",
"line_start": 371,
"line_end": 371,
"snippet": "lines.append(f\"- **`{prop_name}`** (`{prop_type}`){req_marker}: {prop_desc}\")"
},
{
"id": "external_commands:scripts/mcp-client.py:377:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "scripts/mcp-client.py",
"line_start": 377,
"line_end": 379,
"snippet": "lines.append(\"```json\")"
},
{
"id": "network:scripts/mcp-client.py:146:http-client-library",
"category": "network",
"severity": "low",
"pattern": "HTTP client library",
"file": "scripts/mcp-client.py",
"line_start": 146,
"line_end": 146,
"snippet": "def request(self, method: str, params: Optional[dict] = None) -> dict:"
},
{
"id": "network:scripts/mcp-client.py:271:http-client-library",
"category": "network",
"severity": "low",
"pattern": "HTTP client library",
"file": "scripts/mcp-client.py",
"line_start": 271,
"line_end": 271,
"snippet": "def request(self, method: str, params: Optional[dict] = None) -> dict:"
},
{
"id": "network:scripts/mcp-client.py:314:http-client-library",
"category": "network",
"severity": "low",
"pattern": "HTTP client library",
"file": "scripts/mcp-client.py",
"line_start": 314,
"line_end": 314,
"snippet": "result = self.transport.request(\"tools/list\")"
},
{
"id": "network:scripts/mcp-client.py:323:http-client-library",
"category": "network",
"severity": "low",
"pattern": "HTTP client library",
"file": "scripts/mcp-client.py",
"line_start": 323,
"line_end": 323,
"snippet": "result = self.transport.request(\"tools/call\", params)"
},
{
"id": "network:scripts/mcp-client.py:328:http-client-library",
"category": "network",
"severity": "low",
"pattern": "HTTP client library",
"file": "scripts/mcp-client.py",
"line_start": 328,
"line_end": 328,
"snippet": "result = self.transport.request(\"resources/list\")"
},
{
"id": "network:scripts/mcp-client.py:333:http-client-library",
"category": "network",
"severity": "low",
"pattern": "HTTP client library",
"file": "scripts/mcp-client.py",
"line_start": 333,
"line_end": 333,
"snippet": "result = self.transport.request(\"prompts/list\")"
},
{
"id": "network:scripts/mcp-client.py:33:python-http-libraries",
"category": "network",
"severity": "low",
"pattern": "Python HTTP libraries",
"file": "scripts/mcp-client.py",
"line_start": 33,
"line_end": 33,
"snippet": "from urllib.request import Request, urlopen"
},
{
"id": "network:scripts/mcp-client.py:10:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "scripts/mcp-client.py",
"line_start": 10,
"line_end": 10,
"snippet": "python mcp-client.py list --url http://localhost:8080"
},
{
"id": "network:scripts/mcp-client.py:16:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "scripts/mcp-client.py",
"line_start": 16,
"line_end": 16,
"snippet": "python mcp-client.py call --url http://localhost:8080 --tool create_issue \\"
},
{
"id": "network:scripts/mcp-client.py:20:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "scripts/mcp-client.py",
"line_start": 20,
"line_end": 20,
"snippet": "python mcp-client.py emit --url http://localhost:8080"
},
{
"id": "network:scripts/mcp-client.py:23:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "scripts/mcp-client.py",
"line_start": 23,
"line_end": 23,
"snippet": "python mcp-client.py emit --url http://localhost:8080 --format json"
},
{
"id": "blocker:scripts/mcp-client.py:52:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "scripts/mcp-client.py",
"line_start": 52,
"line_end": 52,
"snippet": "self._request_id = 0"
},
{
"id": "blocker:scripts/mcp-client.py:57:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "scripts/mcp-client.py",
"line_start": 57,
"line_end": 57,
"snippet": "self._request_id += 1"
},
{
"id": "blocker:scripts/mcp-client.py:58:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "scripts/mcp-client.py",
"line_start": 58,
"line_end": 60,
"snippet": "return self._request_id"
},
{
"id": "blocker:scripts/mcp-client.py:88:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "scripts/mcp-client.py",
"line_start": 88,
"line_end": 88,
"snippet": "self._session_id = resp.headers.get('Mcp-Session-Id')"
},
{
"id": "blocker:scripts/mcp-client.py:137:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "scripts/mcp-client.py",
"line_start": 137,
"line_end": 139,
"snippet": "headers[\"Mcp-Session-Id\"] = self._session_id"
},
{
"id": "blocker:scripts/mcp-client.py:165:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "scripts/mcp-client.py",
"line_start": 165,
"line_end": 167,
"snippet": "headers[\"Mcp-Session-Id\"] = self._session_id"
},
{
"id": "blocker:scripts/mcp-client.py:190:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "scripts/mcp-client.py",
"line_start": 190,
"line_end": 190,
"snippet": "self._request_id = 0"
},
{
"id": "blocker:scripts/mcp-client.py:196:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "scripts/mcp-client.py",
"line_start": 196,
"line_end": 196,
"snippet": "self._request_id += 1"
},
{
"id": "blocker:scripts/mcp-client.py:197:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "scripts/mcp-client.py",
"line_start": 197,
"line_end": 199,
"snippet": "return self._request_id"
},
{
"id": "blocker:scripts/mcp-client.py:275:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "scripts/mcp-client.py",
"line_start": 275,
"line_end": 275,
"snippet": "req_id = self._next_id()"
},
{
"id": "blocker:scripts/mcp-client.py:286:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "scripts/mcp-client.py",
"line_start": 286,
"line_end": 287,
"snippet": "# Wait for response with matching id"
},
{
"id": "blocker:scripts/mcp-client.py:480:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "scripts/mcp-client.py",
"line_start": 480,
"line_end": 480,
"snippet": "print(f\"Invalid JSON: {e}\", file=sys.stderr)"
},
{
"id": "external_commands:scripts/start-server.sh:9:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "scripts/start-server.sh",
"line_start": 9,
"line_end": 9,
"snippet": "if [ -f \"$PID_FILE\" ] && kill -0 $(cat \"$PID_FILE\") 2>/dev/null; then"
},
{
"id": "external_commands:scripts/start-server.sh:10:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "scripts/start-server.sh",
"line_start": 10,
"line_end": 10,
"snippet": "echo \"Playwright MCP already running on port $PORT (PID: $(cat $PID_FILE))\""
},
{
"id": "external_commands:scripts/start-server.sh:20:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "scripts/start-server.sh",
"line_start": 20,
"line_end": 20,
"snippet": "if kill -0 $(cat \"$PID_FILE\") 2>/dev/null; then"
},
{
"id": "external_commands:scripts/start-server.sh:21:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "scripts/start-server.sh",
"line_start": 21,
"line_end": 21,
"snippet": "echo \"Playwright MCP started on port $PORT (PID: $(cat $PID_FILE))\""
},
{
"id": "external_commands:scripts/start-server.sh:1:unix-shell-invocation",
"category": "external_commands",
"severity": "medium",
"pattern": "Unix shell invocation",
"file": "scripts/start-server.sh",
"line_start": 1,
"line_end": 1,
"snippet": "#!/bin/bash"
},
{
"id": "filesystem:scripts/start-server.sh:9:standard-device-file-access",
"category": "filesystem",
"severity": "low",
"pattern": "Standard device file access",
"file": "scripts/start-server.sh",
"line_start": 9,
"line_end": 9,
"snippet": "if [ -f \"$PID_FILE\" ] && kill -0 $(cat \"$PID_FILE\") 2>/dev/null; then"
},
{
"id": "filesystem:scripts/start-server.sh:20:standard-device-file-access",
"category": "filesystem",
"severity": "low",
"pattern": "Standard device file access",
"file": "scripts/start-server.sh",
"line_start": 20,
"line_end": 20,
"snippet": "if kill -0 $(cat \"$PID_FILE\") 2>/dev/null; then"
},
{
"id": "filesystem:scripts/start-server.sh:6:temp-directory-access",
"category": "filesystem",
"severity": "medium",
"pattern": "Temp directory access",
"file": "scripts/start-server.sh",
"line_start": 6,
"line_end": 6,
"snippet": "PID_FILE=\"/tmp/playwright-mcp-${PORT}.pid\""
},
{
"id": "external_commands:scripts/stop-server.sh:9:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "scripts/stop-server.sh",
"line_start": 9,
"line_end": 9,
"snippet": "PID=$(cat \"$PID_FILE\")"
},
{
"id": "external_commands:scripts/stop-server.sh:12:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "scripts/stop-server.sh",
"line_start": 12,
"line_end": 12,
"snippet": "python3 \"$(dirname \"$0\")/mcp-client.py\" call -u \"http://localhost:${PORT}\" -t browser_close -p '{}' "
},
{
"id": "external_commands:scripts/stop-server.sh:1:unix-shell-invocation",
"category": "external_commands",
"severity": "medium",
"pattern": "Unix shell invocation",
"file": "scripts/stop-server.sh",
"line_start": 1,
"line_end": 1,
"snippet": "#!/bin/bash"
},
{
"id": "network:scripts/stop-server.sh:12:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "scripts/stop-server.sh",
"line_start": 12,
"line_end": 12,
"snippet": "python3 \"$(dirname \"$0\")/mcp-client.py\" call -u \"http://localhost:${PORT}\" -t browser_close -p '{}' "
},
{
"id": "filesystem:scripts/stop-server.sh:10:standard-device-file-access",
"category": "filesystem",
"severity": "low",
"pattern": "Standard device file access",
"file": "scripts/stop-server.sh",
"line_start": 10,
"line_end": 10,
"snippet": "if kill -0 \"$PID\" 2>/dev/null; then"
},
{
"id": "filesystem:scripts/stop-server.sh:12:standard-device-file-access",
"category": "filesystem",
"severity": "low",
"pattern": "Standard device file access",
"file": "scripts/stop-server.sh",
"line_start": 12,
"line_end": 12,
"snippet": "python3 \"$(dirname \"$0\")/mcp-client.py\" call -u \"http://localhost:${PORT}\" -t browser_close -p '{}' "
},
{
"id": "filesystem:scripts/stop-server.sh:15:standard-device-file-access",
"category": "filesystem",
"severity": "low",
"pattern": "Standard device file access",
"file": "scripts/stop-server.sh",
"line_start": 15,
"line_end": 15,
"snippet": "kill \"$PID\" 2>/dev/null"
},
{
"id": "filesystem:scripts/stop-server.sh:19:standard-device-file-access",
"category": "filesystem",
"severity": "low",
"pattern": "Standard device file access",
"file": "scripts/stop-server.sh",
"line_start": 19,
"line_end": 19,
"snippet": "kill -9 \"$PID\" 2>/dev/null || true"
},
{
"id": "filesystem:scripts/stop-server.sh:28:standard-device-file-access",
"category": "filesystem",
"severity": "low",
"pattern": "Standard device file access",
"file": "scripts/stop-server.sh",
"line_start": 28,
"line_end": 28,
"snippet": "pkill -f \"@playwright/mcp.*--port.*${PORT}\" 2>/dev/null && echo \"Playwright MCP stopped\" || echo \"Pl"
},
{
"id": "filesystem:scripts/stop-server.sh:6:temp-directory-access",
"category": "filesystem",
"severity": "medium",
"pattern": "Temp directory access",
"file": "scripts/stop-server.sh",
"line_start": 6,
"line_end": 6,
"snippet": "PID_FILE=\"/tmp/playwright-mcp-${PORT}.pid\""
},
{
"id": "external_commands:SKILL.md:13:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 13,
"line_end": 19,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:19:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 19,
"line_end": 22,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:22:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 22,
"line_end": 29,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:29:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 29,
"line_end": 36,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:36:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 36,
"line_end": 42,
"snippet": "**Important:** The `--shared-browser-context` flag is required to maintain browser state across mult"
},
{
"id": "external_commands:SKILL.md:42:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 42,
"line_end": 49,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:49:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 49,
"line_end": 53,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:53:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 53,
"line_end": 60,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:60:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 60,
"line_end": 64,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:64:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 64,
"line_end": 66,
"snippet": "Use `ref` from snapshot output to target elements:"
},
{
"id": "external_commands:SKILL.md:66:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 66,
"line_end": 82,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:82:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 82,
"line_end": 86,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:86:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 86,
"line_end": 94,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:94:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 94,
"line_end": 98,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:98:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 98,
"line_end": 101,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:101:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 101,
"line_end": 105,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:105:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 105,
"line_end": 107,
"snippet": "For complex workflows, use `browser_run_code` to run multiple actions in one call:"
},
{
"id": "external_commands:SKILL.md:107:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 107,
"line_end": 110,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:110:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 110,
"line_end": 112,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:112:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 112,
"line_end": 140,
"snippet": "**Tip:** Use `browser_run_code` for complex multi-step operations that should be atomic (all-or-noth"
},
{
"id": "network:SKILL.md:27:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 27,
"line_end": 27,
"snippet": "python3 scripts/mcp-client.py call -u http://localhost:8808 -t browser_close -p '{}'"
},
{
"id": "network:SKILL.md:44:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 44,
"line_end": 44,
"snippet": "python3 scripts/mcp-client.py call -u http://localhost:8808 -t browser_navigate \\"
},
{
"id": "network:SKILL.md:45:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 45,
"line_end": 45,
"snippet": "-p '{\"url\": \"https://example.com\"}'"
},
{
"id": "network:SKILL.md:48:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 48,
"line_end": 48,
"snippet": "python3 scripts/mcp-client.py call -u http://localhost:8808 -t browser_navigate_back -p '{}'"
},
{
"id": "network:SKILL.md:55:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 55,
"line_end": 55,
"snippet": "python3 scripts/mcp-client.py call -u http://localhost:8808 -t browser_snapshot -p '{}'"
},
{
"id": "network:SKILL.md:58:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 58,
"line_end": 58,
"snippet": "python3 scripts/mcp-client.py call -u http://localhost:8808 -t browser_take_screenshot \\"
},
{
"id": "network:SKILL.md:68:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 68,
"line_end": 68,
"snippet": "python3 scripts/mcp-client.py call -u http://localhost:8808 -t browser_click \\"
},
{
"id": "network:SKILL.md:72:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 72,
"line_end": 72,
"snippet": "python3 scripts/mcp-client.py call -u http://localhost:8808 -t browser_type \\"
},
{
"id": "network:SKILL.md:76:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 76,
"line_end": 76,
"snippet": "python3 scripts/mcp-client.py call -u http://localhost:8808 -t browser_fill_form \\"
},
{
"id": "network:SKILL.md:80:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 80,
"line_end": 80,
"snippet": "python3 scripts/mcp-client.py call -u http://localhost:8808 -t browser_select_option \\"
},
{
"id": "network:SKILL.md:88:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 88,
"line_end": 88,
"snippet": "python3 scripts/mcp-client.py call -u http://localhost:8808 -t browser_wait_for \\"
},
{
"id": "network:SKILL.md:92:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 92,
"line_end": 92,
"snippet": "python3 scripts/mcp-client.py call -u http://localhost:8808 -t browser_wait_for \\"
},
{
"id": "network:SKILL.md:99:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 99,
"line_end": 99,
"snippet": "python3 scripts/mcp-client.py call -u http://localhost:8808 -t browser_evaluate \\"
},
{
"id": "network:SKILL.md:108:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 108,
"line_end": 108,
"snippet": "python3 scripts/mcp-client.py call -u http://localhost:8808 -t browser_run_code \\"
},
{
"id": "network:SKILL.md:109:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 109,
"line_end": 109,
"snippet": "-p '{\"code\": \"async (page) => { await page.goto(\\\"https://example.com\\\"); await page.click(\\\"text=Le"
}
],
"finding_verdicts": [
{
"id": "external_commands:references/playwright-tools.md:247:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The backticks are Markdown or schema documentation syntax, not Ruby or shell execution. This reference file documents MCP tools and does not run commands."
},
{
"id": "external_commands:references/playwright-tools.md:308:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The backticks are Markdown or schema documentation syntax, not Ruby or shell execution. This reference file documents MCP tools and does not run commands."
},
{
"id": "external_commands:references/playwright-tools.md:471:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The backticks are Markdown or schema documentation syntax, not Ruby or shell execution. This reference file documents MCP tools and does not run commands."
},
{
"id": "external_commands:references/playwright-tools.md:515:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The backticks are Markdown or schema documentation syntax, not Ruby or shell execution. This reference file documents MCP tools and does not run commands."
},
{
"id": "network:references/playwright-tools.md:19:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is the JSON Schema identifier inside generated tool documentation. It is metadata and does not cause outbound network activity."
},
{
"id": "network:references/playwright-tools.md:56:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is the JSON Schema identifier inside generated tool documentation. It is metadata and does not cause outbound network activity."
},
{
"id": "network:references/playwright-tools.md:91:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is the JSON Schema identifier inside generated tool documentation. It is metadata and does not cause outbound network activity."
},
{
"id": "network:references/playwright-tools.md:127:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is the JSON Schema identifier inside generated tool documentation. It is metadata and does not cause outbound network activity."
},
{
"id": "network:references/playwright-tools.md:168:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is the JSON Schema identifier inside generated tool documentation. It is metadata and does not cause outbound network activity."
},
{
"id": "network:references/playwright-tools.md:199:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is the JSON Schema identifier inside generated tool documentation. It is metadata and does not cause outbound network activity."
},
{
"id": "network:references/playwright-tools.md:265:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is the JSON Schema identifier inside generated tool documentation. It is metadata and does not cause outbound network activity."
},
{
"id": "network:references/playwright-tools.md:284:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is the JSON Schema identifier inside generated tool documentation. It is metadata and does not cause outbound network activity."
},
{
"id": "network:references/playwright-tools.md:315:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is the JSON Schema identifier inside generated tool documentation. It is metadata and does not cause outbound network activity."
},
{
"id": "network:references/playwright-tools.md:368:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is the JSON Schema identifier inside generated tool documentation. It is metadata and does not cause outbound network activity."
},
{
"id": "network:references/playwright-tools.md:399:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is the JSON Schema identifier inside generated tool documentation. It is metadata and does not cause outbound network activity."
},
{
"id": "network:references/playwright-tools.md:418:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is the JSON Schema identifier inside generated tool documentation. It is metadata and does not cause outbound network activity."
},
{
"id": "network:references/playwright-tools.md:447:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is the JSON Schema identifier inside generated tool documentation. It is metadata and does not cause outbound network activity."
},
{
"id": "network:references/playwright-tools.md:478:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is the JSON Schema identifier inside generated tool documentation. It is metadata and does not cause outbound network activity."
},
{
"id": "network:references/playwright-tools.md:531:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is the JSON Schema identifier inside generated tool documentation. It is metadata and does not cause outbound network activity."
},
{
"id": "network:references/playwright-tools.md:559:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is the JSON Schema identifier inside generated tool documentation. It is metadata and does not cause outbound network activity."
},
{
"id": "network:references/playwright-tools.md:626:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is the JSON Schema identifier inside generated tool documentation. It is metadata and does not cause outbound network activity."
},
{
"id": "network:references/playwright-tools.md:675:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is the JSON Schema identifier inside generated tool documentation. It is metadata and does not cause outbound network activity."
},
{
"id": "network:references/playwright-tools.md:712:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is the JSON Schema identifier inside generated tool documentation. It is metadata and does not cause outbound network activity."
},
{
"id": "network:references/playwright-tools.md:758:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is the JSON Schema identifier inside generated tool documentation. It is metadata and does not cause outbound network activity."
},
{
"id": "network:references/playwright-tools.md:800:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is the JSON Schema identifier inside generated tool documentation. It is metadata and does not cause outbound network activity."
},
{
"id": "network:references/playwright-tools.md:838:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is the JSON Schema identifier inside generated tool documentation. It is metadata and does not cause outbound network activity."
},
{
"id": "external_commands:scripts/mcp-client.py:191:python-subprocess-popen",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "This line is only a type annotation for a Popen handle. The actual process creation is separately adjudicated at the later subprocess.Popen call."
},
{
"id": "external_commands:scripts/mcp-client.py:204:python-subprocess-popen",
"verdict": "confirmed",
"confidence": 0.86,
"reason": "subprocess.Popen is called with shell=True on the caller-provided --stdio command. This can execute arbitrary shell syntax if untrusted input reaches that option.",
"severity": "high"
},
{
"id": "external_commands:scripts/mcp-client.py:348:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.94,
"reason": "The line builds Markdown output with inline backticks or code fences. It does not invoke a shell, Ruby interpreter, or subprocess."
},
{
"id": "external_commands:scripts/mcp-client.py:371:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.94,
"reason": "The line builds Markdown output with inline backticks or code fences. It does not invoke a shell, Ruby interpreter, or subprocess."
},
{
"id": "external_commands:scripts/mcp-client.py:377:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.94,
"reason": "The line builds Markdown output with inline backticks or code fences. It does not invoke a shell, Ruby interpreter, or subprocess."
},
{
"id": "network:scripts/mcp-client.py:146:http-client-library",
"verdict": "confirmed",
"confidence": 0.78,
"reason": "This request method builds and sends JSON-RPC calls through the HTTP transport. The destination is caller-controlled through --url, so the network capability is real.",
"severity": "low"
},
{
"id": "network:scripts/mcp-client.py:271:http-client-library",
"verdict": "false_positive",
"confidence": 0.86,
"reason": "This is the StdioTransport request method, not an HTTP request. It writes JSON-RPC to an already started subprocess rather than opening a network connection."
},
{
"id": "network:scripts/mcp-client.py:314:http-client-library",
"verdict": "confirmed",
"confidence": 0.72,
"reason": "The high-level client sends a tools/list request through the selected transport. When HTTP transport is selected, this is outbound network activity to a caller-provided MCP server.",
"severity": "low"
},
{
"id": "network:scripts/mcp-client.py:323:http-client-library",
"verdict": "confirmed",
"confidence": 0.74,
"reason": "The high-level client sends tools/call parameters through the selected transport. With HTTP transport, tool names and arguments are sent to the configured MCP endpoint.",
"severity": "low"
},
{
"id": "network:scripts/mcp-client.py:328:http-client-library",
"verdict": "confirmed",
"confidence": 0.72,
"reason": "The resource listing request is routed through the selected MCP transport. If HTTP is used, the request goes to the caller-provided server URL.",
"severity": "low"
},
{
"id": "network:scripts/mcp-client.py:333:http-client-library",
"verdict": "confirmed",
"confidence": 0.72,
"reason": "The prompt listing request is routed through the selected MCP transport. If HTTP is used, the request goes to the caller-provided server URL.",
"severity": "low"
},
{
"id": "network:scripts/mcp-client.py:33:python-http-libraries",
"verdict": "confirmed",
"confidence": 0.78,
"reason": "The client imports urllib.request and uses it for MCP HTTP transport. Network access is intended, but it is still a real capability that can contact caller-provided URLs.",
"severity": "low"
},
{
"id": "network:scripts/mcp-client.py:10:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.91,
"reason": "The URL appears in CLI usage examples for localhost. Runtime destinations are supplied by the caller through --url."
},
{
"id": "network:scripts/mcp-client.py:16:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.91,
"reason": "The URL appears in CLI usage examples for localhost. Runtime destinations are supplied by the caller through --url."
},
{
"id": "network:scripts/mcp-client.py:20:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.91,
"reason": "The URL appears in CLI usage examples for localhost. Runtime destinations are supplied by the caller through --url."
},
{
"id": "network:scripts/mcp-client.py:23:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.91,
"reason": "The URL appears in CLI usage examples for localhost. Runtime destinations are supplied by the caller through --url."
},
{
"id": "blocker:scripts/mcp-client.py:52:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The line manages JSON-RPC request IDs, MCP session headers, or error output. It does not collect host inventory or perform system reconnaissance."
},
{
"id": "blocker:scripts/mcp-client.py:57:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The line manages JSON-RPC request IDs, MCP session headers, or error output. It does not collect host inventory or perform system reconnaissance."
},
{
"id": "blocker:scripts/mcp-client.py:58:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The line manages JSON-RPC request IDs, MCP session headers, or error output. It does not collect host inventory or perform system reconnaissance."
},
{
"id": "blocker:scripts/mcp-client.py:88:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The line manages JSON-RPC request IDs, MCP session headers, or error output. It does not collect host inventory or perform system reconnaissance."
},
{
"id": "blocker:scripts/mcp-client.py:137:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The line manages JSON-RPC request IDs, MCP session headers, or error output. It does not collect host inventory or perform system reconnaissance."
},
{
"id": "blocker:scripts/mcp-client.py:165:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The line manages JSON-RPC request IDs, MCP session headers, or error output. It does not collect host inventory or perform system reconnaissance."
},
{
"id": "blocker:scripts/mcp-client.py:190:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The line manages JSON-RPC request IDs, MCP session headers, or error output. It does not collect host inventory or perform system reconnaissance."
},
{
"id": "blocker:scripts/mcp-client.py:196:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The line manages JSON-RPC request IDs, MCP session headers, or error output. It does not collect host inventory or perform system reconnaissance."
},
{
"id": "blocker:scripts/mcp-client.py:197:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The line manages JSON-RPC request IDs, MCP session headers, or error output. It does not collect host inventory or perform system reconnaissance."
},
{
"id": "blocker:scripts/mcp-client.py:275:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The line manages JSON-RPC request IDs, MCP session headers, or error output. It does not collect host inventory or perform system reconnaissance."
},
{
"id": "blocker:scripts/mcp-client.py:286:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The line manages JSON-RPC request IDs, MCP session headers, or error output. It does not collect host inventory or perform system reconnaissance."
},
{
"id": "blocker:scripts/mcp-client.py:480:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The line manages JSON-RPC request IDs, MCP session headers, or error output. It does not collect host inventory or perform system reconnaissance."
},
{
"id": "external_commands:scripts/start-server.sh:9:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.82,
"reason": "The command substitution reads a local PID file for status messages or kill -0 checks. The PID file content is not executed as shell code."
},
{
"id": "external_commands:scripts/start-server.sh:10:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.82,
"reason": "The command substitution reads a local PID file for status messages or kill -0 checks. The PID file content is not executed as shell code."
},
{
"id": "external_commands:scripts/start-server.sh:20:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.82,
"reason": "The command substitution reads a local PID file for status messages or kill -0 checks. The PID file content is not executed as shell code."
},
{
"id": "external_commands:scripts/start-server.sh:21:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.82,
"reason": "The command substitution reads a local PID file for status messages or kill -0 checks. The PID file content is not executed as shell code."
},
{
"id": "external_commands:scripts/start-server.sh:1:unix-shell-invocation",
"verdict": "confirmed",
"confidence": 0.8,
"reason": "This shell helper starts the Playwright MCP server through npx in the same script. It intentionally launches local processes and pulls an external package name.",
"severity": "medium"
},
{
"id": "filesystem:scripts/start-server.sh:9:standard-device-file-access",
"verdict": "false_positive",
"confidence": 0.82,
"reason": "This line uses standard shell error redirection while checking process status. The predictable temporary PID file risk is covered by the separate /tmp finding."
},
{
"id": "filesystem:scripts/start-server.sh:20:standard-device-file-access",
"verdict": "false_positive",
"confidence": 0.82,
"reason": "This line uses standard shell error redirection while checking process status. The predictable temporary PID file risk is covered by the separate /tmp finding."
},
{
"id": "filesystem:scripts/start-server.sh:6:temp-directory-access",
"verdict": "confirmed",
"confidence": 0.82,
"reason": "The script stores the server PID in a predictable /tmp path derived from the port. A local user could tamper with that file and affect lifecycle checks.",
"severity": "medium"
},
{
"id": "external_commands:scripts/stop-server.sh:9:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.84,
"reason": "The substitution reads a PID from the known PID file and stores it in a variable. It does not execute the file contents as a command."
},
{
"id": "external_commands:scripts/stop-server.sh:12:shell-command-substitution",
"verdict": "confirmed",
"confidence": 0.72,
"reason": "The line invokes python3 to run the bundled MCP client before stopping the server. The dirname substitution is quoted, but this is still intentional external command execution.",
"severity": "medium"
},
{
"id": "external_commands:scripts/stop-server.sh:1:unix-shell-invocation",
"verdict": "confirmed",
"confidence": 0.78,
"reason": "This shell helper controls processes with kill and pkill in the same script. It is intended lifecycle management, but it is security relevant process control.",
"severity": "medium"
},
{
"id": "network:scripts/stop-server.sh:12:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.88,
"reason": "The hardcoded URL targets localhost to close the local MCP browser session. It is not a hidden external endpoint."
},
{
"id": "filesystem:scripts/stop-server.sh:10:standard-device-file-access",
"verdict": "false_positive",
"confidence": 0.82,
"reason": "The line performs process checks, process signaling, or stderr redirection. The separate predictable /tmp PID file finding captures the relevant filesystem risk."
},
{
"id": "filesystem:scripts/stop-server.sh:12:standard-device-file-access",
"verdict": "false_positive",
"confidence": 0.82,
"reason": "The line performs process checks, process signaling, or stderr redirection. The separate predictable /tmp PID file finding captures the relevant filesystem risk."
},
{
"id": "filesystem:scripts/stop-server.sh:15:standard-device-file-access",
"verdict": "false_positive",
"confidence": 0.82,
"reason": "The line performs process checks, process signaling, or stderr redirection. The separate predictable /tmp PID file finding captures the relevant filesystem risk."
},
{
"id": "filesystem:scripts/stop-server.sh:19:standard-device-file-access",
"verdict": "false_positive",
"confidence": 0.82,
"reason": "The line performs process checks, process signaling, or stderr redirection. The separate predictable /tmp PID file finding captures the relevant filesystem risk."
},
{
"id": "filesystem:scripts/stop-server.sh:28:standard-device-file-access",
"verdict": "false_positive",
"confidence": 0.82,
"reason": "The line performs process checks, process signaling, or stderr redirection. The separate predictable /tmp PID file finding captures the relevant filesystem risk."
},
{
"id": "filesystem:scripts/stop-server.sh:6:temp-directory-access",
"verdict": "confirmed",
"confidence": 0.84,
"reason": "The stop script trusts a predictable /tmp PID file to choose which process to signal. A tampered PID file could cause it to target an unintended process.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:13:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.82,
"reason": "This Markdown range instructs users or agents to run bash scripts and npx @playwright/mcp@latest. These are real local shell commands, even though the static pattern name is imprecise.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:19:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.84,
"reason": "The backticks in this range are Markdown formatting or prose around documented commands. No additional executable command is introduced by this specific finding."
},
{
"id": "external_commands:SKILL.md:22:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.82,
"reason": "This Markdown range instructs stopping the server with bash, python3, and pkill commands. Those commands intentionally execute local processes and signal matching processes.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:29:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.84,
"reason": "The backticks in this range are Markdown formatting or prose around documented commands. No additional executable command is introduced by this specific finding."
},
{
"id": "external_commands:SKILL.md:36:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.84,
"reason": "The backticks in this range are Markdown formatting or prose around documented commands. No additional executable command is introduced by this specific finding."
},
{
"id": "external_commands:SKILL.md:42:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.74,
"reason": "The range contains shell examples that call scripts/mcp-client.py for browser navigation. This is intended tooling, but it directs agents to execute local commands.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:49:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.84,
"reason": "The backticks in this range are Markdown formatting or prose around documented commands. No additional executable command is introduced by this specific finding."
},
{
"id": "external_commands:SKILL.md:53:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.72,
"reason": "The range contains shell examples that call the MCP client for snapshots and screenshots. It is legitimate documentation, but it still asks the agent to run local commands.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:60:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.84,
"reason": "The backticks in this range are Markdown formatting or prose around documented commands. No additional executable command is introduced by this specific finding."
},
{
"id": "external_commands:SKILL.md:64:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.84,
"reason": "The backticks in this range are Markdown formatting or prose around documented commands. No additional executable command is introduced by this specific finding."
},
{
"id": "external_commands:SKILL.md:66:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.78,
"reason": "The range contains shell commands for clicking, typing, filling forms, and selecting options. These commands can change live web pages and submit user data.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:82:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.84,
"reason": "The backticks in this range are Markdown formatting or prose around documented commands. No additional executable command is introduced by this specific finding."
},
{
"id": "external_commands:SKILL.md:86:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.68,
"reason": "The range contains shell examples that invoke the MCP client for wait operations. The action is low impact, but it still directs local command execution.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:94:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.84,
"reason": "The backticks in this range are Markdown formatting or prose around documented commands. No additional executable command is introduced by this specific finding."
},
{
"id": "external_commands:SKILL.md:98:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.84,
"reason": "The range documents browser_evaluate with caller-supplied JavaScript. In an active browser context, JavaScript can inspect or manipulate page state.",
"severity": "high"
},
{
"id": "external_commands:SKILL.md:101:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.84,
"reason": "The backticks in this range are Markdown formatting or prose around documented commands. No additional executable command is introduced by this specific finding."
},
{
"id": "external_commands:SKILL.md:105:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.82,
"reason": "The prose recommends browser_run_code for complex multi-step browser workflows. That tool runs supplied Playwright code and can perform powerful page actions.",
"severity": "high"
},
{
"id": "external_commands:SKILL.md:107:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.86,
"reason": "The range shows browser_run_code executing supplied Playwright code through the MCP client. This can perform arbitrary browser actions in the current page context.",
"severity": "high"
},
{
"id": "external_commands:SKILL.md:110:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.84,
"reason": "The backticks in this range are Markdown formatting or prose around documented commands. No additional executable command is introduced by this specific finding."
},
{
"id": "external_commands:SKILL.md:112:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.84,
"reason": "The backticks in this range are Markdown formatting or prose around documented commands. No additional executable command is introduced by this specific finding."
},
{
"id": "network:SKILL.md:27:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The URL is localhost or example.com in usage documentation. It is not a hidden destination or credential exfiltration endpoint."
},
{
"id": "network:SKILL.md:44:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The URL is localhost or example.com in usage documentation. It is not a hidden destination or credential exfiltration endpoint."
},
{
"id": "network:SKILL.md:45:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The URL is localhost or example.com in usage documentation. It is not a hidden destination or credential exfiltration endpoint."
},
{
"id": "network:SKILL.md:48:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The URL is localhost or example.com in usage documentation. It is not a hidden destination or credential exfiltration endpoint."
},
{
"id": "network:SKILL.md:55:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The URL is localhost or example.com in usage documentation. It is not a hidden destination or credential exfiltration endpoint."
},
{
"id": "network:SKILL.md:58:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The URL is localhost or example.com in usage documentation. It is not a hidden destination or credential exfiltration endpoint."
},
{
"id": "network:SKILL.md:68:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The URL is localhost or example.com in usage documentation. It is not a hidden destination or credential exfiltration endpoint."
},
{
"id": "network:SKILL.md:72:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The URL is localhost or example.com in usage documentation. It is not a hidden destination or credential exfiltration endpoint."
},
{
"id": "network:SKILL.md:76:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The URL is localhost or example.com in usage documentation. It is not a hidden destination or credential exfiltration endpoint."
},
{
"id": "network:SKILL.md:80:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The URL is localhost or example.com in usage documentation. It is not a hidden destination or credential exfiltration endpoint."
},
{
"id": "network:SKILL.md:88:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The URL is localhost or example.com in usage documentation. It is not a hidden destination or credential exfiltration endpoint."
},
{
"id": "network:SKILL.md:92:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The URL is localhost or example.com in usage documentation. It is not a hidden destination or credential exfiltration endpoint."
},
{
"id": "network:SKILL.md:99:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The URL is localhost or example.com in usage documentation. It is not a hidden destination or credential exfiltration endpoint."
},
{
"id": "network:SKILL.md:108:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The URL is localhost or example.com in usage documentation. It is not a hidden destination or credential exfiltration endpoint."
},
{
"id": "network:SKILL.md:109:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The URL is localhost or example.com in usage documentation. It is not a hidden destination or credential exfiltration endpoint."
}
],
"semantic_findings": [
{
"title": "Arbitrary Browser JavaScript Execution",
"description": "The skill documents browser_evaluate and browser_run_code for caller-supplied JavaScript and Playwright code. In an authenticated browser, this can read page content or perform unintended actions.",
"severity": "high",
"locations": [
{
"file": "SKILL.md",
"line_start": 98,
"line_end": 109
},
{
"file": "references/playwright-tools.md",
"line_start": 452,
"line_end": 471
}
],
"confidence": 0.88,
"confidence_reasoning": "The referenced lines explicitly document executing supplied browser JavaScript or Playwright code. The risk depends on target page context, but the capability is direct and powerful."
},
{
"title": "Persistent Shared Browser Context",
"description": "The skill requires shared browser context across MCP calls. This can retain cookies, logged-in state, and other session data longer than users expect.",
"severity": "medium",
"locations": [
{
"file": "SKILL.md",
"line_start": 36,
"line_end": 36
},
{
"file": "scripts/start-server.sh",
"line_start": 15,
"line_end": 15
}
],
"confidence": 0.82,
"confidence_reasoning": "The instructions state that shared browser context is required, and the start script enables it. Persistent state is intentional, but it is security-sensitive for authenticated sessions."
}
],
"critical_findings": [],
"high_findings": [
{
"title": "Python subprocess.Popen",
"description": "self._process = subprocess.Popen(",
"locations": [
{
"file": "scripts/mcp-client.py",
"line_start": 204,
"line_end": 204
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "high",
"confidence": 0.86,
"confidence_reasoning": "subprocess.Popen is called with shell=True on the caller-provided --stdio command. This can execute arbitrary shell syntax if untrusted input reaches that option."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 98,
"line_end": 101
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.84,
"confidence_reasoning": "The range documents browser_evaluate with caller-supplied JavaScript. In an active browser context, JavaScript can inspect or manipulate page state."
},
{
"title": "Ruby/shell backtick execution",
"description": "For complex workflows, use `browser_run_code` to run multiple actions in one call:",
"locations": [
{
"file": "SKILL.md",
"line_start": 105,
"line_end": 107
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.82,
"confidence_reasoning": "The prose recommends browser_run_code for complex multi-step browser workflows. That tool runs supplied Playwright code and can perform powerful page actions."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 107,
"line_end": 110
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.86,
"confidence_reasoning": "The range shows browser_run_code executing supplied Playwright code through the MCP client. This can perform arbitrary browser actions in the current page context."
},
{
"title": "Arbitrary Browser JavaScript Execution",
"description": "The skill documents browser_evaluate and browser_run_code for caller-supplied JavaScript and Playwright code. In an authenticated browser, this can read page content or perform unintended actions.",
"locations": [
{
"file": "SKILL.md",
"line_start": 98,
"line_end": 109
},
{
"file": "references/playwright-tools.md",
"line_start": 452,
"line_end": 471
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "high",
"confidence": 0.88,
"confidence_reasoning": "The referenced lines explicitly document executing supplied browser JavaScript or Playwright code. The risk depends on target page context, but the capability is direct and powerful."
}
],
"medium_findings": [
{
"title": "Unix shell invocation",
"description": "#!/bin/bash",
"locations": [
{
"file": "scripts/start-server.sh",
"line_start": 1,
"line_end": 1
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.8,
"confidence_reasoning": "This shell helper starts the Playwright MCP server through npx in the same script. It intentionally launches local processes and pulls an external package name."
},
{
"title": "Temp directory access",
"description": "PID_FILE=\"/tmp/playwright-mcp-${PORT}.pid\"",
"locations": [
{
"file": "scripts/start-server.sh",
"line_start": 6,
"line_end": 6
}
],
"review_kind": "capability",
"source_category": "filesystem",
"source_severity": "medium",
"confidence": 0.82,
"confidence_reasoning": "The script stores the server PID in a predictable /tmp path derived from the port. A local user could tamper with that file and affect lifecycle checks."
},
{
"title": "Shell command substitution",
"description": "python3 \"$(dirname \"$0\")/mcp-client.py\" call -u \"http://localhost:${PORT}\" -t browser_close -p '{}' ",
"locations": [
{
"file": "scripts/stop-server.sh",
"line_start": 12,
"line_end": 12
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.72,
"confidence_reasoning": "The line invokes python3 to run the bundled MCP client before stopping the server. The dirname substitution is quoted, but this is still intentional external command execution."
},
{
"title": "Unix shell invocation",
"description": "#!/bin/bash",
"locations": [
{
"file": "scripts/stop-server.sh",
"line_start": 1,
"line_end": 1
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.78,
"confidence_reasoning": "This shell helper controls processes with kill and pkill in the same script. It is intended lifecycle management, but it is security relevant process control."
},
{
"title": "Temp directory access",
"description": "PID_FILE=\"/tmp/playwright-mcp-${PORT}.pid\"",
"locations": [
{
"file": "scripts/stop-server.sh",
"line_start": 6,
"line_end": 6
}
],
"review_kind": "capability",
"source_category": "filesystem",
"source_severity": "medium",
"confidence": 0.84,
"confidence_reasoning": "The stop script trusts a predictable /tmp PID file to choose which process to signal. A tampered PID file could cause it to target an unintended process."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 13,
"line_end": 19
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.82,
"confidence_reasoning": "This Markdown range instructs users or agents to run bash scripts and npx @playwright/mcp@latest. These are real local shell commands, even though the static pattern name is imprecise."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 22,
"line_end": 29
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.82,
"confidence_reasoning": "This Markdown range instructs stopping the server with bash, python3, and pkill commands. Those commands intentionally execute local processes and signal matching processes."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 42,
"line_end": 49
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.74,
"confidence_reasoning": "The range contains shell examples that call scripts/mcp-client.py for browser navigation. This is intended tooling, but it directs agents to execute local commands."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 53,
"line_end": 60
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.72,
"confidence_reasoning": "The range contains shell examples that call the MCP client for snapshots and screenshots. It is legitimate documentation, but it still asks the agent to run local commands."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 66,
"line_end": 82
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.78,
"confidence_reasoning": "The range contains shell commands for clicking, typing, filling forms, and selecting options. These commands can change live web pages and submit user data."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 86,
"line_end": 94
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.68,
"confidence_reasoning": "The range contains shell examples that invoke the MCP client for wait operations. The action is low impact, but it still directs local command execution."
},
{
"title": "Persistent Shared Browser Context",
"description": "The skill requires shared browser context across MCP calls. This can retain cookies, logged-in state, and other session data longer than users expect.",
"locations": [
{
"file": "SKILL.md",
"line_start": 36,
"line_end": 36
},
{
"file": "scripts/start-server.sh",
"line_start": 15,
"line_end": 15
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "medium",
"confidence": 0.82,
"confidence_reasoning": "The instructions state that shared browser context is required, and the start script enables it. Persistent state is intentional, but it is security-sensitive for authenticated sessions."
}
],
"low_findings": [
{
"title": "HTTP client library",
"description": "def request(self, method: str, params: Optional[dict] = None) -> dict:",
"locations": [
{
"file": "scripts/mcp-client.py",
"line_start": 146,
"line_end": 146
}
],
"review_kind": "capability",
"source_category": "network",
"source_severity": "low",
"confidence": 0.78,
"confidence_reasoning": "This request method builds and sends JSON-RPC calls through the HTTP transport. The destination is caller-controlled through --url, so the network capability is real."
},
{
"title": "HTTP client library",
"description": "result = self.transport.request(\"tools/list\")",
"locations": [
{
"file": "scripts/mcp-client.py",
"line_start": 314,
"line_end": 314
}
],
"review_kind": "capability",
"source_category": "network",
"source_severity": "low",
"confidence": 0.72,
"confidence_reasoning": "The high-level client sends a tools/list request through the selected transport. When HTTP transport is selected, this is outbound network activity to a caller-provided MCP server."
},
{
"title": "HTTP client library",
"description": "result = self.transport.request(\"tools/call\", params)",
"locations": [
{
"file": "scripts/mcp-client.py",
"line_start": 323,
"line_end": 323
}
],
"review_kind": "capability",
"source_category": "network",
"source_severity": "low",
"confidence": 0.74,
"confidence_reasoning": "The high-level client sends tools/call parameters through the selected transport. With HTTP transport, tool names and arguments are sent to the configured MCP endpoint."
},
{
"title": "HTTP client library",
"description": "result = self.transport.request(\"resources/list\")",
"locations": [
{
"file": "scripts/mcp-client.py",
"line_start": 328,
"line_end": 328
}
],
"review_kind": "capability",
"source_category": "network",
"source_severity": "low",
"confidence": 0.72,
"confidence_reasoning": "The resource listing request is routed through the selected MCP transport. If HTTP is used, the request goes to the caller-provided server URL."
},
{
"title": "HTTP client library",
"description": "result = self.transport.request(\"prompts/list\")",
"locations": [
{
"file": "scripts/mcp-client.py",
"line_start": 333,
"line_end": 333
}
],
"review_kind": "capability",
"source_category": "network",
"source_severity": "low",
"confidence": 0.72,
"confidence_reasoning": "The prompt listing request is routed through the selected MCP transport. If HTTP is used, the request goes to the caller-provided server URL."
},
{
"title": "Python HTTP libraries",
"description": "from urllib.request import Request, urlopen",
"locations": [
{
"file": "scripts/mcp-client.py",
"line_start": 33,
"line_end": 33
}
],
"review_kind": "capability",
"source_category": "network",
"source_severity": "low",
"confidence": 0.78,
"confidence_reasoning": "The client imports urllib.request and uses it for MCP HTTP transport. Network access is intended, but it is still a real capability that can contact caller-provided URLs."
}
],
"dangerous_patterns": [],
"files_scanned": 5,
"total_lines": 1533,
"audit_model": "codex",
"audited_at": "2026-07-07T18:25:44.347Z",
"agent_auto_install_policy": "confirmation_required",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Automate Browser Workflows with Playwright MCP",
"value_statement": "Manual browser workflows are slow and hard to repeat. This skill provides Playwright MCP commands for navigation, forms, screenshots, and extraction.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"browser automation",
"Playwright MCP",
"web scraping",
"form automation",
"UI testing",
"MCP client",
"screenshot capture"
],
"actual_capabilities": [
"Start and stop a local Playwright MCP server with helper scripts.",
"Call MCP tools over HTTP or stdio with JSON parameters.",
"Navigate pages, manage tabs, click elements, type text, and fill forms.",
"Capture screenshots, accessibility snapshots, console messages, and network request lists.",
"Generate Markdown or JSON documentation from MCP tool schemas.",
"Run browser_evaluate and browser_run_code for advanced Playwright actions."
],
"limitations": [
"Requires Node.js, Playwright MCP, Python, and a runnable browser environment.",
"Browser actions can affect live sites and authenticated sessions.",
"Stdio mode can execute shell commands supplied by the caller.",
"The skill does not enforce rate limits, consent rules, or site terms."
],
"use_cases": [
{
"title": "Test Web Workflows",
"target_user": "QA engineers",
"description": "Validate login, search, checkout, and regression flows with repeatable browser actions."
},
{
"title": "Collect Public Page Data",
"target_user": "Researchers and analysts",
"description": "Collect public page snapshots, screenshots, and visible structured data for analysis."
},
{
"title": "Debug Web Applications",
"target_user": "Frontend developers",
"description": "Inspect UI states, console messages, and network activity during debugging."
}
],
"prompt_templates": [
{
"title": "Open a Page",
"scenario": "Beginner navigation",
"prompt": "Start the Playwright MCP server, open [URL], capture a snapshot, and summarize the visible page state."
},
{
"title": "Fill a Form",
"scenario": "Guided form task",
"prompt": "Open [URL], get a snapshot, fill these fields: [fields], submit only after confirmation, and capture a screenshot."
},
{
"title": "Extract Visible Data",
"scenario": "Structured research",
"prompt": "Visit [URL], collect the visible data matching [criteria], note pagination, and return concise findings with source page names."
},
{
"title": "Run a Multi-Step Workflow",
"scenario": "Advanced automation",
"prompt": "Use browser_run_code only for this approved workflow: [steps]. Avoid sensitive fields, record each page reached, and stop the server when complete."
}
],
"output_examples": [
{
"input": "Open a product page and capture a full-page screenshot.",
"output": "The browser opened the product page, captured a full-page screenshot, and reported the main headings and visible calls to action."
},
{
"input": "Submit a demo contact form after I approve the filled fields.",
"output": "The form fields were filled, approval was requested before submission, and a confirmation screenshot was captured after submit."
},
{
"input": "Extract visible article titles from a news category page.",
"output": "Returned a concise list of visible article titles, source section names, and notes about pagination."
}
],
"best_practices": [
"Run browser_snapshot before clicking or typing so element references are current.",
"Use approved domains and staging environments for tests that submit forms.",
"Stop the MCP server and clear browser state after sensitive work."
],
"anti_patterns": [
"Do not browse authenticated accounts or submit credentials without explicit user approval.",
"Do not pass untrusted text into the stdio command option.",
"Do not use browser_run_code when a named browser tool can complete the task."
],
"faq": [
{
"question": "What does this skill automate?",
"answer": "It automates browser navigation, element interaction, screenshots, and data extraction through Playwright MCP."
},
{
"question": "Does it need a local server?",
"answer": "Yes. The helper scripts start a local Playwright MCP server on the configured port."
},
{
"question": "Can it use authenticated sessions?",
"answer": "Yes, but only with user approval. Shared browser context can retain cookies and logged-in state."
},
{
"question": "Can it scrape websites?",
"answer": "It can collect visible page data, but users must follow site terms, laws, and rate limits."
},
{
"question": "Is browser_run_code required?",
"answer": "No. Use named browser tools for simple tasks and reserve browser_run_code for complex approved workflows."
},
{
"question": "Which AI tools can use it?",
"answer": "The report lists Claude, Codex, and Claude Code as supported tools."
}
]
},
"file_structure": [
{
"name": "references",
"type": "dir",
"path": "references",
"children": [
{
"name": "playwright-tools.md",
"type": "file",
"path": "references/playwright-tools.md",
"lines": 843
}
]
},
{
"name": "scripts",
"type": "dir",
"path": "scripts",
"children": [
{
"name": "mcp-client.py",
"type": "file",
"path": "scripts/mcp-client.py",
"lines": 491
},
{
"name": "start-server.sh",
"type": "file",
"path": "scripts/start-server.sh",
"lines": 27
},
{
"name": "stop-server.sh",
"type": "file",
"path": "scripts/stop-server.sh",
"lines": 30
}
]
},
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 142
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |