Caveat verdict

metaskill

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

The skill has executionSinkDetected=true for deep self-correction and transfer learning, but seems to be for legitimate AI learning enhancement.

⚠ 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.

55
security
90
transparency
70
maintenance

Findings (4)

Pattern match high

Uses eval() — can execute arbitrary code

config.yaml · prose · downgraded · eval (

Pattern match high

Pipe to python — executes piped content as Python code

scripts/deep-correct.sh · prose · downgraded · | python3

Pattern match low

Python os.environ.get — reads environment variable

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

Pattern match low

Python urllib.request — network access

scripts/llm_provider.py · prose · downgraded · urllib.request

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class C). 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