aiskillstore/marketplace / skills/101-skills/python-executor
python-executor
VerifiedExecute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh). Pre-installed: NumPy, Pandas, Matplotlib, requests, BeautifulSoup, Selenium, Playwright, MoviePy, Pillow, OpenCV, trimesh, and 100+ more libraries. Use for: data processing, web scraping, image manipulation, video creation, 3D model processing, PDF generation, API calls, automation scripts. Triggers: python, execute code, run script, web scraping, data analysis, image processing, video editing, 3D models, automation, pandas, matplotlib
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.0 KB |
| skill-report.json | config | 55.9 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-12T10:13:22.264Z",
"slug": "101-skills-python-executor",
"source_url": "https://github.com/101-skills/skills/tree/main/tools/utilities/python-executor/",
"source_ref": "main",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "07b9c819e9fc35546b8660b4b05a139a0b370711ab655436f329c1aebad97674",
"tree_hash": "e7dfc159ab8ec1467df6a41d7d9453591d31715785fa4a066460349610403e6f",
"provenance": {
"model_effective": "codex",
"fallback_chain": [
{
"agent": "codex",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "python-executor",
"description": "Run Python 3.10 code through the inference.sh executor with preinstalled libraries for data, web, media, documents, and 3D processing.",
"summary": "Execute Python workloads remotely and return console output or generated files.",
"icon": "📦",
"version": "1.0.2",
"author": "101-skills",
"license": "MIT",
"category": "coding",
"tags": [
"python",
"code-execution",
"data-analysis",
"automation",
"sandbox"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"external_commands",
"network"
]
},
"security_audit": {
"risk_level": "medium",
"is_blocked": false,
"safe_to_publish": true,
"analysis_status": "ok",
"summary": "The skill intentionally invokes the belt CLI, submits arbitrary Python to a third-party execution service, and demonstrates outbound HTTP requests. Most backtick detections are Markdown formatting, and the reconnaissance alert is unsupported, but remote execution, network access, and unpinned npx installation remain real risks.",
"remediation": [
{
"issue": "Python source and embedded data are submitted to a third-party execution service.",
"suggestion": "Disclose the remote processing boundary and instruct users to remove secrets, credentials, and sensitive data before execution.",
"severity": "medium"
},
{
"issue": "Generated Python can make outbound network requests from the execution environment.",
"suggestion": "Require explicit approval for network access and recommend domain allowlists, request timeouts, and response size limits.",
"severity": "medium"
},
{
"issue": "The installation guidance executes an unpinned package through npx.",
"suggestion": "Pin the installer package to a reviewed version and provide checksum or provenance verification instructions.",
"severity": "medium"
}
],
"risk_factor_evidence": [
{
"factor": "external_commands",
"evidence": [
{
"file": "SKILL.md",
"line_start": 7,
"line_end": 7
},
{
"file": "SKILL.md",
"line_start": 17,
"line_end": 17
},
{
"file": "SKILL.md",
"line_start": 19,
"line_end": 26
},
{
"file": "SKILL.md",
"line_start": 26,
"line_end": 33
},
{
"file": "SKILL.md",
"line_start": 33,
"line_end": 40
},
{
"file": "SKILL.md",
"line_start": 40,
"line_end": 47
},
{
"file": "SKILL.md",
"line_start": 47,
"line_end": 52
},
{
"file": "SKILL.md",
"line_start": 52,
"line_end": 52
},
{
"file": "SKILL.md",
"line_start": 53,
"line_end": 53
},
{
"file": "SKILL.md",
"line_start": 54,
"line_end": 54
},
{
"file": "SKILL.md",
"line_start": 55,
"line_end": 58
},
{
"file": "SKILL.md",
"line_start": 58,
"line_end": 58
},
{
"file": "SKILL.md",
"line_start": 59,
"line_end": 59
},
{
"file": "SKILL.md",
"line_start": 62,
"line_end": 62
},
{
"file": "SKILL.md",
"line_start": 63,
"line_end": 63
},
{
"file": "SKILL.md",
"line_start": 66,
"line_end": 67
},
{
"file": "SKILL.md",
"line_start": 67,
"line_end": 67
},
{
"file": "SKILL.md",
"line_start": 68,
"line_end": 71
},
{
"file": "SKILL.md",
"line_start": 71,
"line_end": 71
},
{
"file": "SKILL.md",
"line_start": 72,
"line_end": 72
},
{
"file": "SKILL.md",
"line_start": 75,
"line_end": 75
},
{
"file": "SKILL.md",
"line_start": 76,
"line_end": 76
},
{
"file": "SKILL.md",
"line_start": 82,
"line_end": 86
},
{
"file": "SKILL.md",
"line_start": 86,
"line_end": 90
},
{
"file": "SKILL.md",
"line_start": 90,
"line_end": 94
},
{
"file": "SKILL.md",
"line_start": 94,
"line_end": 98
},
{
"file": "SKILL.md",
"line_start": 98,
"line_end": 102
},
{
"file": "SKILL.md",
"line_start": 102,
"line_end": 106
},
{
"file": "SKILL.md",
"line_start": 106,
"line_end": 111
},
{
"file": "SKILL.md",
"line_start": 111,
"line_end": 115
},
{
"file": "SKILL.md",
"line_start": 115,
"line_end": 119
},
{
"file": "SKILL.md",
"line_start": 119,
"line_end": 123
},
{
"file": "SKILL.md",
"line_start": 123,
"line_end": 127
},
{
"file": "SKILL.md",
"line_start": 127,
"line_end": 131
},
{
"file": "SKILL.md",
"line_start": 131,
"line_end": 133
},
{
"file": "SKILL.md",
"line_start": 133,
"line_end": 139
},
{
"file": "SKILL.md",
"line_start": 139,
"line_end": 143
},
{
"file": "SKILL.md",
"line_start": 143,
"line_end": 149
},
{
"file": "SKILL.md",
"line_start": 149,
"line_end": 166
},
{
"file": "SKILL.md",
"line_start": 166,
"line_end": 166
},
{
"file": "SKILL.md",
"line_start": 171,
"line_end": 180
}
]
},
{
"factor": "network",
"evidence": [
{
"file": "SKILL.md",
"line_start": 84,
"line_end": 84
},
{
"file": "SKILL.md",
"line_start": 125,
"line_end": 125
},
{
"file": "SKILL.md",
"line_start": 3,
"line_end": 3
},
{
"file": "SKILL.md",
"line_start": 13,
"line_end": 13
},
{
"file": "SKILL.md",
"line_start": 17,
"line_end": 17
},
{
"file": "SKILL.md",
"line_start": 84,
"line_end": 84
},
{
"file": "SKILL.md",
"line_start": 125,
"line_end": 125
},
{
"file": "SKILL.md",
"line_start": 184,
"line_end": 184
},
{
"file": "SKILL.md",
"line_start": 185,
"line_end": 185
},
{
"file": "SKILL.md",
"line_start": 186,
"line_end": 186
}
]
}
],
"static_findings": [
{
"id": "external_commands:SKILL.md:7:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 7,
"line_end": 7,
"snippet": "> **Install the belt CLI skill:** `npx skills add belt-sh/cli`"
},
{
"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": 17,
"snippet": "> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/infer"
},
{
"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": 26,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 26,
"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": 40,
"snippet": "| App ID | `infsh/python-executor` |"
},
{
"id": "external_commands:SKILL.md:40:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 40,
"line_end": 47,
"snippet": "```json"
},
{
"id": "external_commands:SKILL.md:47:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 47,
"line_end": 52,
"snippet": "```"
},
{
"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": 52,
"snippet": "- `requests`, `httpx`, `aiohttp` - HTTP clients"
},
{
"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": 53,
"snippet": "- `beautifulsoup4`, `lxml` - HTML/XML parsing"
},
{
"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": "- `selenium`, `playwright` - Browser automation"
},
{
"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": 58,
"snippet": "- `scrapy` - Web scraping framework"
},
{
"id": "external_commands:SKILL.md:58:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 58,
"line_end": 58,
"snippet": "- `numpy`, `pandas`, `scipy` - Numerical computing"
},
{
"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": 59,
"snippet": "- `matplotlib`, `seaborn`, `plotly` - Visualization"
},
{
"id": "external_commands:SKILL.md:62:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 62,
"line_end": 62,
"snippet": "- `pillow`, `opencv-python-headless` - Image manipulation"
},
{
"id": "external_commands:SKILL.md:63:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 63,
"line_end": 63,
"snippet": "- `scikit-image`, `imageio` - Image algorithms"
},
{
"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": 67,
"snippet": "- `moviepy` - Video editing"
},
{
"id": "external_commands:SKILL.md:67:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 67,
"line_end": 67,
"snippet": "- `av` (PyAV), `ffmpeg-python` - Video processing"
},
{
"id": "external_commands:SKILL.md:68:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 68,
"line_end": 71,
"snippet": "- `pydub` - Audio manipulation"
},
{
"id": "external_commands:SKILL.md:71:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 71,
"line_end": 71,
"snippet": "- `trimesh`, `open3d` - 3D mesh processing"
},
{
"id": "external_commands:SKILL.md:72:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 72,
"line_end": 72,
"snippet": "- `numpy-stl`, `meshio`, `pyvista` - 3D file formats"
},
{
"id": "external_commands:SKILL.md:75:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 75,
"line_end": 75,
"snippet": "- `svgwrite`, `cairosvg` - SVG creation"
},
{
"id": "external_commands:SKILL.md:76:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 76,
"line_end": 76,
"snippet": "- `reportlab`, `pypdf2` - PDF generation"
},
{
"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": "```bash"
},
{
"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": 90,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:90:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 90,
"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": 102,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:102:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 102,
"line_end": 106,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:106:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 106,
"line_end": 111,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:111:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 111,
"line_end": 115,
"snippet": "```"
},
{
"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": 119,
"snippet": "```bash"
},
{
"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": 123,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:123:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 123,
"line_end": 127,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:127:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 127,
"line_end": 131,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:131:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 131,
"line_end": 133,
"snippet": "Files saved to `outputs/` are automatically returned:"
},
{
"id": "external_commands:SKILL.md:133:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 133,
"line_end": 139,
"snippet": "```python"
},
{
"id": "external_commands:SKILL.md:139:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 139,
"line_end": 143,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:143:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 143,
"line_end": 149,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:149:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 149,
"line_end": 166,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:166:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 166,
"line_end": 166,
"snippet": "- **Non-interactive** - Use `plt.savefig()` not `plt.show()`"
},
{
"id": "external_commands:SKILL.md:171:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 171,
"line_end": 180,
"snippet": "```bash"
},
{
"id": "network:SKILL.md:84:python-http-libraries",
"category": "network",
"severity": "low",
"pattern": "Python HTTP libraries",
"file": "SKILL.md",
"line_start": 84,
"line_end": 84,
"snippet": "\"code\": \"import requests\\nfrom bs4 import BeautifulSoup\\n\\nresponse = requests.get(\\\"https://example"
},
{
"id": "network:SKILL.md:125:python-http-libraries",
"category": "network",
"severity": "low",
"pattern": "Python HTTP libraries",
"file": "SKILL.md",
"line_start": 125,
"line_end": 125,
"snippet": "\"code\": \"import requests\\nimport json\\n\\nresponse = requests.get(\\\"https://api.github.com/users/octo"
},
{
"id": "network:SKILL.md:3:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 3,
"line_end": 3,
"snippet": "description: \"Execute Python code in a safe sandboxed environment via [inference.sh](https://inferen"
},
{
"id": "network:SKILL.md:13:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 13,
"line_end": 13,
"snippet": ". [Install instructions](https://raw.githubusercontent.com/infer"
},
{
"id": "network:SKILL.md:84:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 84,
"line_end": 84,
"snippet": "\"code\": \"import requests\\nfrom bs4 import BeautifulSoup\\n\\nresponse = requests.get(\\\"https://example"
},
{
"id": "network:SKILL.md:125:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 125,
"line_end": 125,
"snippet": "\"code\": \"import requests\\nimport json\\n\\nresponse = requests.get(\\\"https://api.github.com/users/octo"
},
{
"id": "network:SKILL.md:184:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 184,
"line_end": 184,
"snippet": "- [Running Apps](https://inference.sh/docs/apps/running) - How to run apps via CLI"
},
{
"id": "network:SKILL.md:185:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 185,
"line_end": 185,
"snippet": "- [App Code](https://inference.sh/docs/extend/app-code) - Understanding app execution"
},
{
"id": "network:SKILL.md:186:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 186,
"line_end": 186,
"snippet": "- [Sandboxed Code Execution](https://inference.sh/blog/tools/sandboxed-execution) - Safe code execut"
},
{
"id": "blocker:SKILL.md:165:network-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "Network reconnaissance",
"file": "SKILL.md",
"line_start": 165,
"line_end": 166,
"snippet": "- **Safe execution** - Runs in isolated subprocess"
}
],
"finding_verdicts": [
{
"id": "external_commands:SKILL.md:7:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.98,
"reason": "Line 7 instructs users to execute an npx package installer, which runs third-party code and creates a supply-chain risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:17:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The backticks only format the belt executable name; line 17 does not execute a shell command."
},
{
"id": "external_commands:SKILL.md:19:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.99,
"reason": "The fenced shell example runs belt login and belt app run, so external command execution is an intended capability.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 26 is only the closing delimiter of a Markdown code fence and does not execute a command."
},
{
"id": "external_commands:SKILL.md:33:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Backticks format the application identifier in a documentation table; no shell evaluation occurs."
},
{
"id": "external_commands:SKILL.md:40:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 40 opens a JSON documentation fence and contains no executable shell command."
},
{
"id": "external_commands:SKILL.md:47:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 47 closes a JSON Markdown fence and does not invoke an external process."
},
{
"id": "external_commands:SKILL.md:52:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Backticks format Python library names in prose; they are not shell execution syntax in this context."
},
{
"id": "external_commands:SKILL.md:53:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Backticks format Python package names in a library list and do not execute commands."
},
{
"id": "external_commands:SKILL.md:54:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The marked terms are documented Python browser libraries, not shell substitutions."
},
{
"id": "external_commands:SKILL.md:55:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The backticks only format the scrapy package name in prose."
},
{
"id": "external_commands:SKILL.md:58:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line lists Python numerical libraries with Markdown formatting and performs no execution."
},
{
"id": "external_commands:SKILL.md:59:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line lists visualization libraries; the backticks are inline Markdown formatting."
},
{
"id": "external_commands:SKILL.md:62:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line documents image libraries and does not contain executable shell syntax."
},
{
"id": "external_commands:SKILL.md:63:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The backticks format package names in prose and cannot invoke an external process."
},
{
"id": "external_commands:SKILL.md:66:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line only identifies the moviepy library with Markdown formatting."
},
{
"id": "external_commands:SKILL.md:67:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The marked text names Python video packages and is not shell backtick execution."
},
{
"id": "external_commands:SKILL.md:68:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Backticks format the pydub package name; no command is invoked."
},
{
"id": "external_commands:SKILL.md:71:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line documents 3D Python libraries and contains no shell evaluation."
},
{
"id": "external_commands:SKILL.md:72:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line is a formatted package list, not an instruction to run external commands."
},
{
"id": "external_commands:SKILL.md:75:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The backticks identify graphics libraries in prose and have no execution semantics."
},
{
"id": "external_commands:SKILL.md:76:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line lists document libraries using Markdown formatting and does not run a command."
},
{
"id": "external_commands:SKILL.md:82:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.99,
"reason": "The fenced example invokes belt app run to execute supplied Python through an external application.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:86:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 86 only closes the preceding shell example and adds no separate command."
},
{
"id": "external_commands:SKILL.md:90:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.99,
"reason": "The fenced example invokes belt app run with generated analysis code, confirming external command execution.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:94:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 94 is a Markdown fence delimiter and does not itself invoke a command."
},
{
"id": "external_commands:SKILL.md:98:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.99,
"reason": "The fenced example calls belt app run to execute image-processing code through an external service.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:102:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 102 is only the closing marker for a code sample."
},
{
"id": "external_commands:SKILL.md:106:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.99,
"reason": "The example executes belt app run with Python video-generation code, which is an external command.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:111:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 111 closes a Markdown shell fence and does not represent another execution."
},
{
"id": "external_commands:SKILL.md:115:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.99,
"reason": "The sample invokes belt app run to execute 3D-processing Python in an external environment.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:119:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 119 is a closing code fence and has no independent command behavior."
},
{
"id": "external_commands:SKILL.md:123:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.99,
"reason": "The sample runs belt app run and submits Python that makes an external API request.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:127:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 127 only terminates the preceding Markdown code block."
},
{
"id": "external_commands:SKILL.md:131:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Backticks format the outputs directory name in prose and do not execute shell code."
},
{
"id": "external_commands:SKILL.md:133:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This is a Python example showing file output methods, not Ruby or shell backtick execution."
},
{
"id": "external_commands:SKILL.md:139:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 139 is the closing delimiter of a Python code block."
},
{
"id": "external_commands:SKILL.md:143:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.99,
"reason": "The shell sample invokes belt app run for both default and high-memory remote variants.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:149:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 149 only closes the shell example and contains no additional command."
},
{
"id": "external_commands:SKILL.md:166:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Backticks format Python plotting method names in an operational note."
},
{
"id": "external_commands:SKILL.md:171:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.98,
"reason": "The fenced examples execute three npx installation commands, which run packages from an external registry.",
"severity": "medium"
},
{
"id": "network:SKILL.md:84:python-http-libraries",
"verdict": "confirmed",
"confidence": 0.99,
"reason": "The Python sample imports requests and performs an outbound GET request to example.com.",
"severity": "low"
},
{
"id": "network:SKILL.md:125:python-http-libraries",
"verdict": "confirmed",
"confidence": 0.99,
"reason": "The Python sample uses requests to call the public GitHub API.",
"severity": "low"
},
{
"id": "network:SKILL.md:3:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The URL is a descriptive link to the named service and does not initiate a request from skill code."
},
{
"id": "network:SKILL.md:13:hardcoded-url",
"verdict": "confirmed",
"confidence": 0.95,
"reason": "The remote image URL may be fetched when the skill documentation is rendered, creating an external request and tracking surface.",
"severity": "low"
},
{
"id": "network:SKILL.md:17:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This is a visible installation documentation link and does not automatically fetch or execute its target."
},
{
"id": "network:SKILL.md:84:hardcoded-url",
"verdict": "confirmed",
"confidence": 0.99,
"reason": "The URL is passed directly to requests.get in executable example code, producing an outbound network request.",
"severity": "low"
},
{
"id": "network:SKILL.md:125:hardcoded-url",
"verdict": "confirmed",
"confidence": 0.99,
"reason": "The hardcoded GitHub API URL is passed to requests.get and is actively contacted by the example.",
"severity": "low"
},
{
"id": "network:SKILL.md:184:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The URL is a documentation hyperlink and is not used by executable code."
},
{
"id": "network:SKILL.md:185:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The URL is a reference link for users and does not cause programmatic network access."
},
{
"id": "network:SKILL.md:186:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The URL points to explanatory documentation and is not fetched by skill code."
},
{
"id": "blocker:SKILL.md:165:network-reconnaissance",
"verdict": "false_positive",
"confidence": 1,
"reason": "The text states that execution uses an isolated subprocess; it contains no host discovery, scanning, or reconnaissance instruction."
}
],
"semantic_findings": [
{
"title": "Third-Party Code Submission Boundary",
"description": "The skill sends Python source through the inference.sh belt application. Submitted source may contain user data or secrets that cross a third-party service boundary.",
"severity": "medium",
"locations": [
{
"file": "SKILL.md",
"line_start": 3,
"line_end": 3
},
{
"file": "SKILL.md",
"line_start": 22,
"line_end": 25
}
],
"confidence": 0.92,
"confidence_reasoning": "The description names inference.sh, and the quick start submits Python source with belt app run. The document does not state a local-only execution path."
}
],
"critical_findings": [],
"high_findings": [],
"medium_findings": [
{
"title": "Ruby/shell backtick execution",
"description": "> **Install the belt CLI skill:** `npx skills add belt-sh/cli`",
"locations": [
{
"file": "SKILL.md",
"line_start": 7,
"line_end": 7
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.98,
"confidence_reasoning": "Line 7 instructs users to execute an npx package installer, which runs third-party code and creates a supply-chain risk."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 19,
"line_end": 26
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.99,
"confidence_reasoning": "The fenced shell example runs belt login and belt app run, so external command execution is an intended capability."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 82,
"line_end": 86
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.99,
"confidence_reasoning": "The fenced example invokes belt app run to execute supplied Python through an external application."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 90,
"line_end": 94
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.99,
"confidence_reasoning": "The fenced example invokes belt app run with generated analysis code, confirming external command execution."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 98,
"line_end": 102
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.99,
"confidence_reasoning": "The fenced example calls belt app run to execute image-processing code through an external service."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 106,
"line_end": 111
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.99,
"confidence_reasoning": "The example executes belt app run with Python video-generation code, which is an external command."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 115,
"line_end": 119
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.99,
"confidence_reasoning": "The sample invokes belt app run to execute 3D-processing Python in an external environment."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 123,
"line_end": 127
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.99,
"confidence_reasoning": "The sample runs belt app run and submits Python that makes an external API request."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 143,
"line_end": 149
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.99,
"confidence_reasoning": "The shell sample invokes belt app run for both default and high-memory remote variants."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 171,
"line_end": 180
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.98,
"confidence_reasoning": "The fenced examples execute three npx installation commands, which run packages from an external registry."
},
{
"title": "Third-Party Code Submission Boundary",
"description": "The skill sends Python source through the inference.sh belt application. Submitted source may contain user data or secrets that cross a third-party service boundary.",
"locations": [
{
"file": "SKILL.md",
"line_start": 3,
"line_end": 3
},
{
"file": "SKILL.md",
"line_start": 22,
"line_end": 25
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "medium",
"confidence": 0.92,
"confidence_reasoning": "The description names inference.sh, and the quick start submits Python source with belt app run. The document does not state a local-only execution path."
}
],
"low_findings": [
{
"title": "Python HTTP libraries",
"description": "\"code\": \"import requests\\nfrom bs4 import BeautifulSoup\\n\\nresponse = requests.get(\\\"https://example",
"locations": [
{
"file": "SKILL.md",
"line_start": 84,
"line_end": 84
}
],
"review_kind": "capability",
"source_category": "network",
"source_severity": "low",
"confidence": 0.99,
"confidence_reasoning": "The Python sample imports requests and performs an outbound GET request to example.com."
},
{
"title": "Python HTTP libraries",
"description": "\"code\": \"import requests\\nimport json\\n\\nresponse = requests.get(\\\"https://api.github.com/users/octo",
"locations": [
{
"file": "SKILL.md",
"line_start": 125,
"line_end": 125
}
],
"review_kind": "capability",
"source_category": "network",
"source_severity": "low",
"confidence": 0.99,
"confidence_reasoning": "The Python sample uses requests to call the public GitHub API."
},
{
"title": "Hardcoded URL",
"description": "![Python Code Executor](https://cloud.inference.sh/u/33sqbmzt3mrg2xxphnhw5g5ear/01k8d8b4mckh6z89dhtx",
"locations": [
{
"file": "SKILL.md",
"line_start": 13,
"line_end": 13
}
],
"review_kind": "capability",
"source_category": "network",
"source_severity": "low",
"confidence": 0.95,
"confidence_reasoning": "The remote image URL may be fetched when the skill documentation is rendered, creating an external request and tracking surface."
},
{
"title": "Hardcoded URL",
"description": "\"code\": \"import requests\\nfrom bs4 import BeautifulSoup\\n\\nresponse = requests.get(\\\"https://example",
"locations": [
{
"file": "SKILL.md",
"line_start": 84,
"line_end": 84
}
],
"review_kind": "capability",
"source_category": "network",
"source_severity": "low",
"confidence": 0.99,
"confidence_reasoning": "The URL is passed directly to requests.get in executable example code, producing an outbound network request."
},
{
"title": "Hardcoded URL",
"description": "\"code\": \"import requests\\nimport json\\n\\nresponse = requests.get(\\\"https://api.github.com/users/octo",
"locations": [
{
"file": "SKILL.md",
"line_start": 125,
"line_end": 125
}
],
"review_kind": "capability",
"source_category": "network",
"source_severity": "low",
"confidence": 0.99,
"confidence_reasoning": "The hardcoded GitHub API URL is passed to requests.get and is actively contacted by the example."
}
],
"dangerous_patterns": [],
"files_scanned": 1,
"total_lines": 188,
"audit_model": "codex",
"audited_at": "2026-07-12T10:13:22.264Z",
"agent_auto_install_policy": "allowed",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Run Python Workloads in a Remote Sandbox",
"value_statement": "Complex Python tasks often require libraries and an isolated runtime. This skill submits code to inference.sh and returns console output or generated files.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"Python executor",
"sandboxed Python",
"data analysis",
"web scraping",
"image processing",
"automation scripts"
],
"actual_capabilities": [
"Runs Python 3.10 code through the infsh/python-executor application.",
"Processes and visualizes data with NumPy, Pandas, SciPy, Matplotlib, Seaborn, and Plotly.",
"Makes HTTP requests and parses web content with common Python libraries.",
"Creates image, video, audio, document, and 3D model files.",
"Returns files written to the outputs directory with captured console output."
],
"limitations": [
"Requires the belt CLI, an inference.sh account, and network access.",
"Uses a CPU-only remote environment without GPU machine learning libraries.",
"Supports non-interactive execution with a maximum documented timeout of 300 seconds.",
"Submitted code and embedded data are processed by a third-party service."
],
"use_cases": [
{
"title": "Analyze Operational Data",
"description": "Clean a dataset, calculate summary metrics, and generate charts without preparing a local Python environment.",
"target_user": "Business analysts"
},
{
"title": "Automate Web Research",
"description": "Request approved public pages, parse selected fields, and return a structured summary.",
"target_user": "Researchers"
},
{
"title": "Generate Technical Assets",
"description": "Create images, PDF reports, short videos, or 3D model exports from defined inputs.",
"target_user": "Developers and creators"
}
],
"prompt_templates": [
{
"title": "Run a Simple Calculation",
"prompt": "Use the Python executor to calculate [calculation]. Show the result and briefly explain the method.",
"scenario": "A beginner needs a verified numerical result."
},
{
"title": "Summarize a Dataset",
"prompt": "Analyze [dataset description] with Pandas. Report missing values, key statistics, and notable patterns. Do not include sensitive data.",
"scenario": "An analyst needs a concise data quality and trend review."
},
{
"title": "Create a Downloadable Report",
"prompt": "Process [input data] and create a PDF report in the outputs directory. Include [sections] and charts for [metrics].",
"scenario": "A user needs a generated document and supporting visuals."
},
{
"title": "Build a Controlled Research Pipeline",
"prompt": "Request only [approved domains], enforce timeouts and response limits, extract [fields], validate results, and save the final table to outputs.",
"scenario": "An advanced user needs a bounded network data workflow."
}
],
"output_examples": [
{
"input": "Analyze monthly sales by region and create a chart.",
"output": [
"Console summary: West had the highest total sales, followed by North.",
"Returned file: regional-sales.png",
"Returned file: regional-sales-summary.csv"
]
},
{
"input": "Create a grayscale gradient image.",
"output": "The execution completed successfully and returned gradient.png from the outputs directory."
},
{
"input": "Inspect a 3D sphere model and report its size.",
"output": "The result reports vertex and face counts, bounding dimensions, and a returned sphere.stl file."
}
],
"best_practices": [
"Remove credentials and sensitive data before submitting code or inputs.",
"Set the shortest practical timeout and write required artifacts to the outputs directory.",
"Use approved domains, request timeouts, and response size limits for network tasks."
],
"anti_patterns": [
"Do not place API keys, tokens, passwords, or private records inside submitted code.",
"Do not scrape restricted sites or bypass access controls and usage policies.",
"Do not rely on interactive windows, GPU acceleration, or unlimited execution time."
],
"faq": [
{
"question": "Does this skill run Python locally?",
"answer": "No. It uses the belt CLI to submit code to the inference.sh Python executor."
},
{
"question": "Which Python version is available?",
"answer": "The documented environment uses Python 3.10."
},
{
"question": "Can it install additional packages?",
"answer": "The skill documents more than 100 pre-installed libraries but does not document runtime package installation."
},
{
"question": "How are generated files returned?",
"answer": "Files written to the outputs directory are detected and included in the execution response."
},
{
"question": "Can it access websites and APIs?",
"answer": "Yes. Included HTTP libraries can make network requests, subject to service controls and target policies."
},
{
"question": "Is sensitive data safe to submit?",
"answer": "Treat execution as third-party processing. Remove secrets and confidential data unless service terms and organizational policies permit submission."
}
]
},
"file_structure": [
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 188
}
]
}
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: 319k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 319k | 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: 196k | Updated | Claude CodeCodex | Verified | Install |