Caveat verdict

auto-skill-evolver

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

A meta-skill that iteratively improves skill files using local CLI commands with explicit security warnings, human-review flags, and shell-injection rejection; modifies only the user's own local skill files with user approval.

⚠ 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.

65
security
100
transparency
90
maintenance

Findings (4)

Pattern match high

Accesses sensitive system files

scripts/security_utils.py · prose · downgraded · /etc/passwd

Pattern match medium

subprocess execution — runs system commands from Python

scripts/hook_wrapper.py · prose · downgraded · subprocess.run(

Pattern match low

Python os.environ.get — reads environment variable

scripts/security_utils.py · prose · downgraded · os.environ.get(

Pattern match low

Sets world-executable permissions

scripts/security_utils.py · prose · downgraded · chmod 700

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