← All skills
skill-security-auditor
46 / 100 · High risk
Only if you trust the author. Some of what it can do is expected: a coding skill usually runs build and test commands.
By alirezarezvani/claude-skills (GitHub) · coding · 29,577 stars · scanned at commit 91a1dda
Use before installing any skill or plugin from an untrusted source, or when asked if a skill is safe. Scans scripts, SKILL.md and dependencies for exfiltration, dangerous calls and prompt injection with skill_security_auditor.py.
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 coding skill.
Found in 22 places.
Show 17 more
- engineering/skills/skill-security-auditor/SKILL.md, line 128
python3 scripts/skill_security_auditor.py https://github.com/user/skill-repo --skill my-skill --cleanup - engineering/skills/skill-security-auditor/SKILL.md, line 145
for skill in skills/*/; do - engineering/skills/skill-security-auditor/references/threat-model.md, line 51
| Direct exec | `eval()`, `exec()`, `os.system()` | `eval(base64.b64decode("..."))` | - engineering/skills/skill-security-auditor/references/threat-model.md, line 52
| Shell injection | `subprocess(shell=True)` | `subprocess.call(f"echo {user_input}", shell=True)` | - engineering/skills/skill-security-auditor/references/threat-model.md, line 67
| Clipboard | Read clipboard content | `subprocess.run(["xclip", "-o"])` | - engineering/skills/skill-security-auditor/references/threat-model.md, line 124
| Command injection | `os.system()`, `subprocess(shell=True)`, backticks | - engineering/skills/skill-security-auditor/references/threat-model.md, line 237
- Use `subprocess.run()` with list arguments (no shell=True) - engineering/skills/skill-security-auditor/references/threat-model.md, line 246
- Use `eval()`, `exec()`, `os.system()`, or `compile()` - engineering/skills/skill-security-auditor/scripts/skill_security_auditor.py, line 133
"risk": "Arbitrary command execution via os.system()", # noqa: SEC-AUDITOR - engineering/skills/skill-security-auditor/scripts/skill_security_auditor.py, line 134
"fix": "Use subprocess.run() with list arguments and shell=False", # noqa: SEC-AUDITOR - engineering/skills/skill-security-auditor/scripts/skill_security_auditor.py, line 140
"risk": "Command execution via os.popen()", # noqa: SEC-AUDITOR - engineering/skills/skill-security-auditor/scripts/skill_security_auditor.py, line 141
"fix": "Use subprocess.run() with list arguments and capture_output=True", # noqa: SEC-AUDITOR - engineering/skills/skill-security-auditor/scripts/skill_security_auditor.py, line 147
"risk": "Shell injection via subprocess with shell=True", # noqa: SEC-AUDITOR - engineering/skills/skill-security-auditor/scripts/skill_security_auditor.py, line 148
"fix": "Use subprocess.run() with list arguments and shell=False", # noqa: SEC-AUDITOR - engineering/skills/skill-security-auditor/scripts/skill_security_auditor.py, line 155
"fix": "Use subprocess.run() with list arguments", # noqa: SEC-AUDITOR - engineering/skills/skill-security-auditor/scripts/skill_security_auditor.py, line 580
"risk": "Node.js child_process — command execution", # noqa: SEC-AUDITOR - engineering/skills/skill-security-auditor/scripts/skill_security_auditor.py, line 581
"fix": "Remove child_process usage or justify with explicit documentation", # noqa: SEC-AUDITOR
and 2 more places
Sends data to these websites: evil.com, analytics.evil.com, setup.evil.com
This is disclosed by the author in the skill's SKILL.md or README.
Found in 9 places.
Show 6 more
Downloads and installs other software
The author does not mention this.
Found in 5 places.
Show 2 more
Reads your saved credentials, such as SSH keys or .env files
This is disclosed by the author in the skill's SKILL.md or README.
Found in 1 place.
Contains code that is hidden or hard to read
This is disclosed by the author in the skill's SKILL.md or README.
Found in 2 places.
Changes files outside its own folder
The author does not mention this.
Found in 1 place.
Safer alternatives
Low-risk skills in the same category (coding) that look related. Check that one does what you need.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'skill-security-auditor' ] || [ -L ~/.agents/skills/'skill-security-auditor' ]; then echo 'A skill folder named skill-security-auditor already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/alirezarezvani/claude-skills' "$d" && git -C "$d" checkout --quiet '91a1ddaab1ae8fe95b8ecd3e98419458db86a992' -- 'engineering/skills/skill-security-auditor' && mkdir -p ~/.agents/skills && cp -R "$d"/'engineering/skills/skill-security-auditor' ~/.agents/skills/'skill-security-auditor' && 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/'skill-security-auditor' ~/.claude/skills/'skill-security-auditor' (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 alirezarezvani/claude-skills shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/alirezarezvani/claude-skills/)
Score history
| Date | Version | Score |
|---|
| 2026-11-10 | 91a1dda | 46 |
| 2026-11-08 | 8f08254 | 46 |
| 2026-11-06 | 8f08254 | 46 |