Scans AI agent skills for security issues:
# Scan any skill directory
python3 scripts/vetter.py /path/to/installed/skill
# JSON output for piping
python3 scripts/vetter.py /path/to/skill --json
| ID | Severity | What It Finds |
|---|---|---|
| --- | --- | --- |
| hardcoded-api-key | high | api_key, api-key |
| hardcoded-secret | high | secret_key, secret-token, auth_token |
| hardcoded-password | high | password |
| unsafe-eval | critical | eval( |
| unsafe-exec | critical | exec( |
| unsafe-os-system | critical | os.system( |
| subprocess-shell-true | high | shell=True |
| raw-network | medium | urllib.request, requests.post/get |
| prompt-injection | critical | ignore previous instructions, ignore the above |
Scanned 12 files in 23ms
Found 1 issue(s):
[CRITICAL] unsafe-eval at /skill/scripts/mail.py:45
→ eval() can execute arbitrary code (matched: 'eval(')
| Feature | Pro ($49) |
|---|---|
| --- | --- |
| Real-time scanning | ✅ |
| Weekly signature updates | ✅ |
| Team sharing | ✅ |
| Custom signatures | ✅ |
| Priority support | ✅ |
Built by CertainLogic
共 1 个版本