code-safety-audit

92 / 100 · Low risk

Fine to try. Some of what it can do is expected: a security skill usually runs scanners and checks websites.

By rongxinzy/RongxinAI (GitHub) · security · 162 stars · scanned at commit 95313ba

扫描代码安全漏洞，检测依赖漏洞、密钥泄露和OWASP安全模式。当用户提到安全扫描、漏洞检测、依赖审计、密钥泄露、API key、OWASP、npm audit、pip-audit或SQL注入/XSS等关键词时触发。

Works with any agent that supports SKILL.md skills.

What this skill can do

Runs commands on your computer

This is disclosed by the author in the skill's SKILL.md or README. Expected for a security skill.

Found in 8 places.

SKILLs/code-safety-audit/SKILL.md, line 19python3 scripts/security_scan.py .
SKILLs/code-safety-audit/scripts/security_scan.py, line 212"name": "Command Injection (subprocess shell=True)",
SKILLs/code-safety-audit/scripts/security_scan.py, line 233"name": "Command Injection (child_process.exec)",

Show 5 more

SKILLs/code-safety-audit/scripts/security_scan.py, line 235"pattern": r"child_process\.exec\s*\(",
SKILLs/code-safety-audit/scripts/security_scan.py, line 488result = subprocess.run(
SKILLs/code-safety-audit/scripts/security_scan.py, line 496except (subprocess.TimeoutExpired, json.JSONDecodeError, OSError) as exc:
SKILLs/code-safety-audit/scripts/security_scan.py, line 537result = subprocess.run(
SKILLs/code-safety-audit/scripts/security_scan.py, line 545except (subprocess.TimeoutExpired, json.JSONDecodeError, OSError) as exc:

Connects to the internet

The author does not mention this. Expected for a security skill.

Found in 1 place.

SKILLs/code-safety-audit/scripts/security_scan.py, line 368"pattern": r"(?:requests\.get|requests\.post|fetch|urllib\.request\.urlopen|http\.get)\s*\(\s*(?:req\.|request\.|params|query|body|user)",

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'code-safety-audit' ] || [ -L ~/.agents/skills/'code-safety-audit' ]; then echo 'A skill folder named code-safety-audit already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/rongxinzy/RongxinAI' "$d" && git -C "$d" checkout --quiet '95313ba7e60af96e152aa42321640b4de7782f4e' -- 'SKILLs/code-safety-audit' && mkdir -p ~/.agents/skills && cp -R "$d"/'SKILLs/code-safety-audit' ~/.agents/skills/'code-safety-audit' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'code-safety-audit' ~/.claude/skills/'code-safety-audit' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for rongxinzy/RongxinAI shows the score of its lowest-scoring skill.

SkillTrust badge for rongxinzy/RongxinAI

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/rongxinzy/RongxinAI.svg)](https://zalavijaysinh.github.io/skilltrust/repos/rongxinzy/RongxinAI/)

Score history

Date	Version	Score
2026-11-13	`95313ba`	92