← All skills
skill-security-auditor
54 / 100 · Review before installing
Check before installing. Some of what it can do is expected: a coding skill usually runs build and test commands.
By borghei/Claude-Skills (GitHub) · coding · 1,086 stars · scanned at commit 25bf86b
Security audit and vulnerability scanning for AI agent skills before install. Detects prompt injection, dangerous code, exfiltration, credential harvesting, and supply chain risks. Use when evaluating untrusted skills or gating installs.
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
The author does not mention this. Expected for a coding skill.
Found in 15 places.
Show 12 more
- engineering/skill-security-auditor/assets/sample_malicious_skill/helper.py, line 10
subprocess.run(f"wc -l {path}", shell=True) - engineering/skill-security-auditor/references/audit-output-and-workflow.md, line 43
Pattern: subprocess.run(["ruff", "check", "."]) - engineering/skill-security-auditor/references/audit-output-and-workflow.md, line 44
Note: Safe usage with list args and no shell=True - engineering/skill-security-auditor/references/audit-output-and-workflow.md, line 103
- [ ] No os.system() or subprocess with shell=True - engineering/skill-security-auditor/references/quality-and-best-practices.md, line 38
| False positive on `subprocess.run()` with list arguments | Pattern matches any `subprocess` usage regardless of shell parameter | Verify the call uses a list - engineering/skill-security-auditor/references/threat-model-and-patterns.md, line 11
| **Code execution in scripts** | Skill includes Python/Bash scripts with `eval()`, `os.system()`, or `subprocess` that execute arbitrary commands | CRITICAL | - engineering/skill-security-auditor/scripts/code_scanner.py, line 81
"risk": "Shell command injection via os.system()", - engineering/skill-security-auditor/scripts/code_scanner.py, line 82
"fix": "Use subprocess.run() with a list of arguments and shell=False", - engineering/skill-security-auditor/scripts/code_scanner.py, line 86
"risk": "Shell command injection via os.popen()", - engineering/skill-security-auditor/scripts/code_scanner.py, line 87
"fix": "Use subprocess.run() with a list of arguments and shell=False", - engineering/skill-security-auditor/scripts/code_scanner.py, line 92
"fix": "Remove shell=True and pass command as a list of arguments", - engineering/skill-security-auditor/scripts/code_scanner.py, line 232
"fix": "Ensure command is passed as a list and shell=True is not used",
Sends data to these websites: 198.51.100.7, external.com
This is disclosed by the author in the skill's SKILL.md or README.
Found in 6 places.
Show 3 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 6 places.
Show 3 more
Downloads and installs other software
The author does not mention this.
Found in 2 places.
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 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=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/borghei/Claude-Skills' "$d" && git -C "$d" checkout --quiet '25bf86b89c6c1e63f433a5b65e8cfcb6cf0b7ad3' -- 'engineering/skill-security-auditor' && mkdir -p ~/.agents/skills && cp -R "$d"/'engineering/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 borghei/Claude-Skills shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/borghei/Claude-Skills/)
Score history
| Date | Version | Score |
|---|
| 2026-11-10 | 25bf86b | 54 |
| 2026-11-08 | 2c12c7e | 54 |
| 2026-11-07 | 2c12c7e | 54 |