aiskillstore/marketplace / skills/0xbigboss/web-fetch
web-fetch
VerifiedFetches web content as clean markdown by preferring markdown-native responses and falling back to selector-based HTML extraction. Use for documentation, articles, and reference pages at http/https URLs.
| File | Kind | Size |
|---|---|---|
| .gitignore | other | 21 B |
| SKILL.md | skill md | 3.3 KB |
| fetch.ts | script | 3.4 KB |
| package.json | manifest | 218 B |
| skill-report.json | config | 45.9 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-06T14:13:20.074Z",
"slug": "0xbigboss-web-fetch",
"source_url": "https://github.com/0xBigBoss/claude-code/tree/main/.claude/skills/web-fetch",
"source_ref": "main",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "e5ffcd7285012fda259785da77851b1bc3eccbf3d4632125cd1c97508224e12d",
"tree_hash": "f831ba3cd325fde7b5feaf824a6a6c16ddc54021c9b3631823f87de3606c8813",
"provenance": {
"model_effective": "codex",
"fallback_chain": [
{
"agent": "codex",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "web-fetch",
"description": "Fetches web pages and converts documentation, articles, and reference pages into clean markdown using curl, html2markdown, and a Bun fallback parser.",
"summary": "Fetch web pages and extract readable markdown from documentation and article content.",
"icon": "📦",
"version": "1.0.1",
"author": "0xBigBoss",
"license": "MIT",
"tags": [
"web-fetch",
"markdown",
"documentation",
"content-extraction",
"research"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"external_commands",
"network",
"filesystem"
],
"category": "research"
},
"security_audit": {
"risk_level": "medium",
"is_blocked": false,
"safe_to_publish": true,
"analysis_status": "ok",
"summary": "Most static findings are false positives caused by Markdown code fences, inline code formatting, or TypeScript template literals. The confirmed issues are real network access to user-supplied URLs and a documented shell workflow that uses command substitution with curl. No evidence found for prompt injection text in the reviewed files.",
"remediation": [
{
"issue": "Unvalidated URL input in fetch.ts",
"suggestion": "Validate URLs before fetching. Allow only http and https, reject localhost and private address ranges, and document the network boundary clearly.",
"severity": "medium"
},
{
"issue": "Shell workflow runs curl against arbitrary URLs",
"suggestion": "Prefer the bundled script with validation over copy-pasted shell pipelines. If shell examples remain, require URL validation and keep all expansions quoted.",
"severity": "medium"
},
{
"issue": "Dependency installation guidance runs from a hidden skill directory",
"suggestion": "Document that bun install changes the skill directory and depends on third-party packages. Pin and review dependencies before marketplace publication.",
"severity": "low"
}
],
"risk_factor_evidence": [
{
"factor": "external_commands",
"evidence": [
{
"file": "fetch.ts",
"line_start": 18,
"line_end": 18
},
{
"file": "fetch.ts",
"line_start": 93,
"line_end": 93
},
{
"file": "fetch.ts",
"line_start": 107,
"line_end": 107
},
{
"file": "fetch.ts",
"line_start": 141,
"line_end": 141
},
{
"file": "SKILL.md",
"line_start": 9,
"line_end": 9
},
{
"file": "SKILL.md",
"line_start": 17,
"line_end": 21
},
{
"file": "SKILL.md",
"line_start": 21,
"line_end": 25
},
{
"file": "SKILL.md",
"line_start": 25,
"line_end": 27
},
{
"file": "SKILL.md",
"line_start": 27,
"line_end": 33
},
{
"file": "SKILL.md",
"line_start": 33,
"line_end": 45
},
{
"file": "SKILL.md",
"line_start": 45,
"line_end": 51
},
{
"file": "SKILL.md",
"line_start": 51,
"line_end": 52
},
{
"file": "SKILL.md",
"line_start": 52,
"line_end": 53
},
{
"file": "SKILL.md",
"line_start": 53,
"line_end": 54
},
{
"file": "SKILL.md",
"line_start": 54,
"line_end": 54
},
{
"file": "SKILL.md",
"line_start": 55,
"line_end": 55
},
{
"file": "SKILL.md",
"line_start": 59,
"line_end": 64
},
{
"file": "SKILL.md",
"line_start": 64,
"line_end": 70
},
{
"file": "SKILL.md",
"line_start": 70,
"line_end": 79
},
{
"file": "SKILL.md",
"line_start": 79,
"line_end": 85
},
{
"file": "SKILL.md",
"line_start": 85,
"line_end": 87
},
{
"file": "SKILL.md",
"line_start": 87,
"line_end": 91
},
{
"file": "SKILL.md",
"line_start": 91,
"line_end": 93
},
{
"file": "SKILL.md",
"line_start": 93,
"line_end": 97
},
{
"file": "SKILL.md",
"line_start": 97,
"line_end": 101
},
{
"file": "SKILL.md",
"line_start": 101,
"line_end": 107
},
{
"file": "SKILL.md",
"line_start": 107,
"line_end": 109
},
{
"file": "SKILL.md",
"line_start": 109,
"line_end": 113
},
{
"file": "SKILL.md",
"line_start": 113,
"line_end": 115
},
{
"file": "SKILL.md",
"line_start": 115,
"line_end": 117
},
{
"file": "SKILL.md",
"line_start": 117,
"line_end": 119
},
{
"file": "SKILL.md",
"line_start": 119,
"line_end": 119
},
{
"file": "SKILL.md",
"line_start": 35,
"line_end": 35
},
{
"file": "SKILL.md",
"line_start": 33,
"line_end": 45
}
]
},
{
"factor": "network",
"evidence": [
{
"file": "fetch.ts",
"line_start": 11,
"line_end": 11
},
{
"file": "SKILL.md",
"line_start": 100,
"line_end": 100
}
]
},
{
"factor": "filesystem",
"evidence": [
{
"file": "SKILL.md",
"line_start": 26,
"line_end": 26
},
{
"file": "SKILL.md",
"line_start": 86,
"line_end": 86
},
{
"file": "SKILL.md",
"line_start": 119,
"line_end": 119
},
{
"file": "SKILL.md",
"line_start": 26,
"line_end": 26
},
{
"file": "SKILL.md",
"line_start": 86,
"line_end": 86
},
{
"file": "SKILL.md",
"line_start": 119,
"line_end": 119
},
{
"file": "SKILL.md",
"line_start": 18,
"line_end": 18
},
{
"file": "SKILL.md",
"line_start": 19,
"line_end": 19
},
{
"file": "SKILL.md",
"line_start": 20,
"line_end": 20
}
]
}
],
"static_findings": [
{
"id": "external_commands:fetch.ts:18:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "fetch.ts",
"line_start": 18,
"line_end": 18,
"snippet": "console.error(`Fetch failed: ${response.status} ${response.statusText}`);"
},
{
"id": "external_commands:fetch.ts:93:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "fetch.ts",
"line_start": 93,
"line_end": 93,
"snippet": "return `\\n\\`\\`\\`${lang}\\n${text}\\n\\`\\`\\`\\n`;"
},
{
"id": "external_commands:fetch.ts:107:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "fetch.ts",
"line_start": 107,
"line_end": 107,
"snippet": "return `\\n\\`\\`\\`\\n${text}\\n\\`\\`\\`\\n`;"
},
{
"id": "external_commands:fetch.ts:141:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "fetch.ts",
"line_start": 141,
"line_end": 141,
"snippet": "console.log(`# ${title}\\n`);"
},
{
"id": "network:fetch.ts:11:fetch-api-call",
"category": "network",
"severity": "low",
"pattern": "Fetch API call",
"file": "fetch.ts",
"line_start": 11,
"line_end": 11,
"snippet": "const response = await fetch(url, {"
},
{
"id": "external_commands:SKILL.md:9:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 9,
"line_end": 9,
"snippet": "1. Prefer markdown-native endpoints (`content-type: text/markdown`)"
},
{
"id": "external_commands:SKILL.md:17:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 17,
"line_end": 21,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:21:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 21,
"line_end": 25,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:25:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 25,
"line_end": 27,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:27:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 27,
"line_end": 33,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:33:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 33,
"line_end": 45,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:45:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 45,
"line_end": 51,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:51:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 51,
"line_end": 52,
"snippet": "| platform.claude.com | `#content-container` | - |"
},
{
"id": "external_commands:SKILL.md:52:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 52,
"line_end": 53,
"snippet": "| docs.anthropic.com | `#content-container` | - |"
},
{
"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": 54,
"snippet": "| developer.mozilla.org | `article` | - |"
},
{
"id": "external_commands:SKILL.md:54:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 54,
"line_end": 54,
"snippet": "| github.com (docs) | `article` | `nav,.sidebar` |"
},
{
"id": "external_commands:SKILL.md:55:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 55,
"line_end": 55,
"snippet": "| Generic | `article,main,[role=main]` | `nav,header,footer,script,style` |"
},
{
"id": "external_commands:SKILL.md:59:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 59,
"line_end": 64,
"snippet": "```bash"
},
{
"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": 70,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:70:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 70,
"line_end": 79,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:79:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 79,
"line_end": 85,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:85:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 85,
"line_end": 87,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:87:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 87,
"line_end": 91,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:91:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 91,
"line_end": 93,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:93:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 93,
"line_end": 97,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:97:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 97,
"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": 107,
"snippet": "```"
},
{
"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": 109,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:109:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 109,
"line_end": 113,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:113:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 113,
"line_end": 115,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:115:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 115,
"line_end": 117,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:117:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 117,
"line_end": 119,
"snippet": "**`html2markdown` not found**: Install it, then retry selector-based extraction."
},
{
"id": "external_commands:SKILL.md:119:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 119,
"line_end": 119,
"snippet": "**`bun` or script deps missing**: Run `cd ~/.claude/skills/web-fetch && bun install`."
},
{
"id": "external_commands:SKILL.md:35:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "SKILL.md",
"line_start": 35,
"line_end": 35,
"snippet": "CONTENT_TYPE=\"$(curl -sIL \"$URL\" | awk -F': ' 'tolower($1)==\"content-type\"{print tolower($2)}' | tr "
},
{
"id": "external_commands:SKILL.md:33:template-literal-with-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Template literal with command substitution",
"file": "SKILL.md",
"line_start": 33,
"line_end": 45,
"snippet": "```bash"
},
{
"id": "network:SKILL.md:100:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 100,
"line_end": 100,
"snippet": "--domain \"https://...\" # Convert relative links to absolute"
},
{
"id": "filesystem:SKILL.md:26:hidden-file-in-home-directory",
"category": "filesystem",
"severity": "high",
"pattern": "Hidden file in home directory",
"file": "SKILL.md",
"line_start": 26,
"line_end": 26,
"snippet": "cd ~/.claude/skills/web-fetch && bun install"
},
{
"id": "filesystem:SKILL.md:86:hidden-file-in-home-directory",
"category": "filesystem",
"severity": "high",
"pattern": "Hidden file in home directory",
"file": "SKILL.md",
"line_start": 86,
"line_end": 86,
"snippet": "bun ~/.claude/skills/web-fetch/fetch.ts \"<url>\""
},
{
"id": "filesystem:SKILL.md:119:hidden-file-in-home-directory",
"category": "filesystem",
"severity": "high",
"pattern": "Hidden file in home directory",
"file": "SKILL.md",
"line_start": 119,
"line_end": 119,
"snippet": "**`bun` or script deps missing**: Run `cd ~/.claude/skills/web-fetch && bun install`."
},
{
"id": "filesystem:SKILL.md:26:hidden-file-access",
"category": "filesystem",
"severity": "medium",
"pattern": "Hidden file access",
"file": "SKILL.md",
"line_start": 26,
"line_end": 26,
"snippet": "cd ~/.claude/skills/web-fetch && bun install"
},
{
"id": "filesystem:SKILL.md:86:hidden-file-access",
"category": "filesystem",
"severity": "medium",
"pattern": "Hidden file access",
"file": "SKILL.md",
"line_start": 86,
"line_end": 86,
"snippet": "bun ~/.claude/skills/web-fetch/fetch.ts \"<url>\""
},
{
"id": "filesystem:SKILL.md:119:hidden-file-access",
"category": "filesystem",
"severity": "medium",
"pattern": "Hidden file access",
"file": "SKILL.md",
"line_start": 119,
"line_end": 119,
"snippet": "**`bun` or script deps missing**: Run `cd ~/.claude/skills/web-fetch && bun install`."
},
{
"id": "filesystem:SKILL.md:18:standard-device-file-access",
"category": "filesystem",
"severity": "low",
"pattern": "Standard device file access",
"file": "SKILL.md",
"line_start": 18,
"line_end": 18,
"snippet": "command -v curl >/dev/null || echo \"curl is required\""
},
{
"id": "filesystem:SKILL.md:19:standard-device-file-access",
"category": "filesystem",
"severity": "low",
"pattern": "Standard device file access",
"file": "SKILL.md",
"line_start": 19,
"line_end": 19,
"snippet": "command -v html2markdown >/dev/null || echo \"html2markdown is required for HTML extraction\""
},
{
"id": "filesystem:SKILL.md:20:standard-device-file-access",
"category": "filesystem",
"severity": "low",
"pattern": "Standard device file access",
"file": "SKILL.md",
"line_start": 20,
"line_end": 20,
"snippet": "command -v bun >/dev/null || echo \"bun is required for fetch.ts fallback\""
}
],
"finding_verdicts": [
{
"id": "external_commands:fetch.ts:18:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "Line 18 is a TypeScript template literal used for an error message. It does not execute a shell command or evaluate user input."
},
{
"id": "external_commands:fetch.ts:93:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "Line 93 returns Markdown code fence text from Turndown conversion. The backticks are output formatting, not command execution."
},
{
"id": "external_commands:fetch.ts:107:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "Line 107 returns Markdown code fence text for a preformatted block. It is not shell syntax executed by the runtime."
},
{
"id": "external_commands:fetch.ts:141:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "Line 141 is a TypeScript template literal printed to stdout as a Markdown heading. It does not invoke a shell."
},
{
"id": "network:fetch.ts:11:fetch-api-call",
"verdict": "confirmed",
"confidence": 0.91,
"reason": "The script fetches a URL supplied on the command line without validating scheme, host, or network range. This creates real external network access and possible SSRF in agent environments.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:9:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 9 uses inline Markdown code formatting around a content-type value. It is documentation text, not executable shell syntax."
},
{
"id": "external_commands:SKILL.md:17:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "Line 17 is the opening fence for a Markdown bash example. The fence itself is not Ruby or shell backtick execution."
},
{
"id": "external_commands:SKILL.md:21:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "Line 21 is the closing fence for a Markdown code block. It does not execute any command."
},
{
"id": "external_commands:SKILL.md:25:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "Line 25 is the opening fence for an installation example. The fence is Markdown syntax, not backtick command execution."
},
{
"id": "external_commands:SKILL.md:27:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "Line 27 is the closing fence for an installation example. It is not shell execution."
},
{
"id": "external_commands:SKILL.md:33:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "Line 33 is a Markdown code fence before a shell workflow. The backticks are formatting and are not themselves executed."
},
{
"id": "external_commands:SKILL.md:45:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "Line 45 is the closing fence for the shell workflow example. It is not a shell backtick expression."
},
{
"id": "external_commands:SKILL.md:51:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 51 uses inline Markdown code formatting for a CSS selector. It does not invoke a command."
},
{
"id": "external_commands:SKILL.md:52:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 52 uses inline Markdown code formatting for a CSS selector. There is no executable shell context."
},
{
"id": "external_commands:SKILL.md:53:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 53 uses inline Markdown code formatting for the article selector. It is not command execution."
},
{
"id": "external_commands:SKILL.md:54:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 54 uses inline Markdown code formatting for selectors in a table. It is documentation, not shell execution."
},
{
"id": "external_commands:SKILL.md:55:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 55 uses inline Markdown code formatting for generic selectors. It does not run a command."
},
{
"id": "external_commands:SKILL.md:59:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "Line 59 is the opening fence for a curl and html2markdown example. The fence itself is not executed."
},
{
"id": "external_commands:SKILL.md:64:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "Line 64 is the closing fence for a shell example. It is Markdown syntax only."
},
{
"id": "external_commands:SKILL.md:70:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "Line 70 is the opening fence for selector testing commands. The backticks are Markdown delimiters, not shell execution."
},
{
"id": "external_commands:SKILL.md:79:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "Line 79 is the closing fence for selector testing commands. It is not an executed backtick expression."
},
{
"id": "external_commands:SKILL.md:85:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "Line 85 is a Markdown code fence before a Bun command example. The fence is not command execution."
},
{
"id": "external_commands:SKILL.md:87:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "Line 87 closes a Markdown code block. It has no runtime effect."
},
{
"id": "external_commands:SKILL.md:91:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "Line 91 is a Markdown code fence before a local Bun command. The fence is not shell backtick execution."
},
{
"id": "external_commands:SKILL.md:93:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "Line 93 closes a Markdown code block. It is not executable syntax."
},
{
"id": "external_commands:SKILL.md:97:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "Line 97 is the opening fence for option examples. It does not execute any command."
},
{
"id": "external_commands:SKILL.md:101:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "Line 101 closes the options example. It is Markdown syntax only."
},
{
"id": "external_commands:SKILL.md:107:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "Line 107 is a Markdown code fence before a curl header check. The fence itself is not executed."
},
{
"id": "external_commands:SKILL.md:109:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "Line 109 closes a Markdown code block. It is not shell backtick execution."
},
{
"id": "external_commands:SKILL.md:113:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "Line 113 is a Markdown code fence before a curl troubleshooting command. The fence has no runtime behavior."
},
{
"id": "external_commands:SKILL.md:115:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "Line 115 closes a Markdown code block. It does not execute a command."
},
{
"id": "external_commands:SKILL.md:117:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 117 uses inline Markdown code formatting around a tool name. It is not shell execution."
},
{
"id": "external_commands:SKILL.md:119:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.92,
"reason": "Line 119 uses inline Markdown code formatting inside troubleshooting text. The executable concern is the documented install command, not Ruby or shell backtick execution."
},
{
"id": "external_commands:SKILL.md:35:shell-command-substitution",
"verdict": "confirmed",
"confidence": 0.87,
"reason": "Line 35 uses shell command substitution to run curl, awk, tr, and tail against a user-provided URL. Quoting limits command injection, but it still drives external network commands from skill instructions.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:33:template-literal-with-command-substitution",
"verdict": "confirmed",
"confidence": 0.82,
"reason": "The shell workflow beginning at line 33 includes command substitution and curl calls using the URL variable. This is a real external command workflow, even though most surrounding backticks are Markdown fences.",
"severity": "medium"
},
{
"id": "network:SKILL.md:100:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "Line 100 shows a placeholder value for an html2markdown domain option. It is not a hardcoded destination or hidden outbound request."
},
{
"id": "filesystem:SKILL.md:26:hidden-file-in-home-directory",
"verdict": "false_positive",
"confidence": 0.88,
"reason": "Line 26 references the normal Claude skills directory for installing this skill dependency set. It does not access credential files or arbitrary hidden user data."
},
{
"id": "filesystem:SKILL.md:86:hidden-file-in-home-directory",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "Line 86 runs the bundled script from the standard Claude skills path. This is expected skill execution, not hidden data access."
},
{
"id": "filesystem:SKILL.md:119:hidden-file-in-home-directory",
"verdict": "false_positive",
"confidence": 0.88,
"reason": "Line 119 repeats the normal Claude skills installation path in troubleshooting text. No hidden secrets or unrelated home files are read."
},
{
"id": "filesystem:SKILL.md:26:hidden-file-access",
"verdict": "false_positive",
"confidence": 0.88,
"reason": "The referenced path is the skill installation directory under .claude. It is not an attempt to inspect or modify unrelated hidden files."
},
{
"id": "filesystem:SKILL.md:86:hidden-file-access",
"verdict": "false_positive",
"confidence": 0.9,
"reason": "The command runs this skill's own fetch.ts from the expected .claude skills location. It does not access hidden user data."
},
{
"id": "filesystem:SKILL.md:119:hidden-file-access",
"verdict": "false_positive",
"confidence": 0.88,
"reason": "The troubleshooting command points to the expected .claude skills directory for dependency installation. No sensitive hidden file access is shown."
},
{
"id": "filesystem:SKILL.md:18:standard-device-file-access",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 18 redirects command lookup output to /dev/null. This is a standard harmless availability check."
},
{
"id": "filesystem:SKILL.md:19:standard-device-file-access",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 19 redirects command lookup output to /dev/null. This is a benign prerequisite check."
},
{
"id": "filesystem:SKILL.md:20:standard-device-file-access",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 20 redirects command lookup output to /dev/null. It does not read or write user data."
}
],
"semantic_findings": [
{
"title": "Unvalidated User-Controlled URL Fetching",
"description": "The fallback script reads the URL from process arguments and passes it directly to fetch. This can request internal network hosts if an agent runs it in a privileged environment.",
"severity": "medium",
"locations": [
{
"file": "fetch.ts",
"line_start": 4,
"line_end": 11
}
],
"confidence": 0.9,
"confidence_reasoning": "The data flow is direct from process.argv[2] to fetch without scheme, host, or private network checks. The behavior is intentional for web fetching, but the missing validation creates a clear SSRF-style risk."
}
],
"critical_findings": [],
"high_findings": [],
"medium_findings": [
{
"title": "Fetch API call",
"description": "const response = await fetch(url, {",
"locations": [
{
"file": "fetch.ts",
"line_start": 11,
"line_end": 11
}
],
"review_kind": "capability",
"source_category": "network",
"source_severity": "low",
"confidence": 0.91,
"confidence_reasoning": "The script fetches a URL supplied on the command line without validating scheme, host, or network range. This creates real external network access and possible SSRF in agent environments."
},
{
"title": "Shell command substitution",
"description": "CONTENT_TYPE=\"$(curl -sIL \"$URL\" | awk -F': ' 'tolower($1)==\"content-type\"{print tolower($2)}' | tr ",
"locations": [
{
"file": "SKILL.md",
"line_start": 35,
"line_end": 35
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.87,
"confidence_reasoning": "Line 35 uses shell command substitution to run curl, awk, tr, and tail against a user-provided URL. Quoting limits command injection, but it still drives external network commands from skill instructions."
},
{
"title": "Template literal with command substitution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 33,
"line_end": 45
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.82,
"confidence_reasoning": "The shell workflow beginning at line 33 includes command substitution and curl calls using the URL variable. This is a real external command workflow, even though most surrounding backticks are Markdown fences."
},
{
"title": "Unvalidated User-Controlled URL Fetching",
"description": "The fallback script reads the URL from process arguments and passes it directly to fetch. This can request internal network hosts if an agent runs it in a privileged environment.",
"locations": [
{
"file": "fetch.ts",
"line_start": 4,
"line_end": 11
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "medium",
"confidence": 0.9,
"confidence_reasoning": "The data flow is direct from process.argv[2] to fetch without scheme, host, or private network checks. The behavior is intentional for web fetching, but the missing validation creates a clear SSRF-style risk."
}
],
"low_findings": [],
"dangerous_patterns": [],
"files_scanned": 4,
"total_lines": 281,
"audit_model": "codex",
"audited_at": "2026-07-06T14:13:20.074Z",
"agent_auto_install_policy": "allowed",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Fetch Web Pages as Markdown",
"value_statement": "Web pages often include navigation, scripts, and unrelated layout content. This skill extracts readable page content and returns clean markdown for review or summarization.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"web fetch",
"markdown extraction",
"documentation research",
"HTML to markdown",
"content extraction",
"Bun parser",
"developer docs"
],
"actual_capabilities": [
"Checks whether a URL serves markdown-native content before converting HTML.",
"Uses curl and html2markdown examples for selector-based extraction.",
"Provides known selectors for Claude, Anthropic, MDN, GitHub docs, and generic pages.",
"Includes a Bun fallback script using linkedom and Turndown for HTML parsing.",
"Removes common navigation, headers, footers, scripts, styles, and copy buttons.",
"Preserves fenced code blocks when converting HTML into markdown."
],
"limitations": [
"Does not render client-side JavaScript pages before extraction.",
"Requires local tools such as curl, html2markdown, bun, and installed package dependencies.",
"Does not validate URLs against private networks or sensitive internal hosts.",
"Selector quality depends on each site structure and may need manual adjustment."
],
"use_cases": [
{
"title": "Collect Documentation Context",
"description": "Fetch a documentation page and convert the main content into markdown for an AI coding session.",
"target_user": "Software developer"
},
{
"title": "Prepare Article Notes",
"description": "Extract article text without menus, footers, and page chrome before summarizing or comparing sources.",
"target_user": "Research analyst"
},
{
"title": "Test HTML Selectors",
"description": "Identify the best content selector for a website and verify the markdown output before reuse.",
"target_user": "Technical writer"
}
],
"prompt_templates": [
{
"title": "Fetch One Page",
"scenario": "Beginner request for a single URL",
"prompt": "Fetch this documentation page as clean markdown and summarize the main points: <url>"
},
{
"title": "Use a Known Selector",
"scenario": "Extract content from a supported documentation site",
"prompt": "Fetch this page with the documented selector for its site, then return only the main content: <url>"
},
{
"title": "Find a Better Selector",
"scenario": "The first extraction includes too much page chrome",
"prompt": "Inspect this page for article or main content containers, test a selector, and provide a cleaner markdown extraction: <url>"
},
{
"title": "Compare Extraction Paths",
"scenario": "Advanced troubleshooting for difficult pages",
"prompt": "Check whether this URL is markdown-native, try selector extraction, then use the Bun fallback if needed. Explain which result is cleanest: <url>"
}
],
"output_examples": [
{
"input": "Fetch an API reference page and summarize it.",
"output": "A markdown title, cleaned section headings, preserved code examples, and a short summary of the API behavior."
},
{
"input": "Extract an article that includes navigation and sidebars.",
"output": "The article body without menu links, footer text, script content, or copy button labels."
},
{
"input": "Troubleshoot a page where the generic selector returns empty content.",
"output": "A note that the page may be markdown-native or client-rendered, plus the next extraction method to try."
}
],
"best_practices": [
"Use trusted public http or https URLs when running the fetch workflow.",
"Check response headers first so markdown-native pages are not converted unnecessarily.",
"Review extracted markdown before using it as source material for important work."
],
"anti_patterns": [
"Do not fetch private network URLs, localhost services, or metadata endpoints.",
"Do not assume generic selectors work for every website layout.",
"Do not run dependency installation commands without reviewing package sources first."
],
"faq": [
{
"question": "What does this skill fetch?",
"answer": "It fetches web pages and extracts readable markdown from documentation, articles, and reference pages."
},
{
"question": "Does it work with JavaScript-rendered pages?",
"answer": "No. It does not render browser JavaScript, so pages with loading placeholders may need browser-based tools."
},
{
"question": "Which tools does it require?",
"answer": "The documented workflow uses curl, html2markdown, bun, linkedom, and Turndown."
},
{
"question": "Can it preserve code blocks?",
"answer": "Yes. The Bun fallback includes rules that preserve fenced code blocks during markdown conversion."
},
{
"question": "Is it safe to use with any URL?",
"answer": "No. Avoid localhost, private networks, metadata endpoints, and pages that require sensitive credentials."
},
{
"question": "Does it store fetched content?",
"answer": "No storage behavior is shown. It prints fetched and converted content to standard output."
}
]
},
"file_structure": [
{
"name": ".gitignore",
"type": "file",
"path": ".gitignore",
"lines": 3
},
{
"name": "fetch.ts",
"type": "file",
"path": "fetch.ts",
"lines": 143
},
{
"name": "package.json",
"type": "file",
"path": "package.json",
"lines": 11
},
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 124
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |