Caveat verdict

security-auditor

klemenska-security-auditor

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Security auditing tool that scans installed skills locally using Python scripts; no network calls or credential exfiltration, behavior matches the stated security audit purpose.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
90
transparency
70
maintenance

Findings (8)

Pattern match critical

Uses eval() — can execute arbitrary code

references/rules.md · code · eval(

Pattern match high

Accesses .ssh directory

references/rules.md · code · .ssh/

Pattern match high

os.system/popen — direct OS command execution

references/rules.md · code · os.system(

Pattern match high

subprocess execution — runs system commands from Python

references/rules.md · code · subprocess.run(

Pattern match high

subprocess with shell=True — command injection vector

references/rules.md · code · subprocess.run(f"ls {directory}", shell=True

Pattern match high

Uses exec() — may execute shell commands

references/rules.md · code · exec(

Pattern match medium

Accesses cloud provider credentials

SKILL.md · prose · downgraded · ~/.aws

Pattern match medium

POSTs data to external URL

references/rules.md · code · .post("https://

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API