Caveat verdict

feedback-learning

feedback-learning-v2

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

A zero-LLM feedback learning system that logs user reactions, analyzes patterns, and promotes behavioral rules via local shell scripts and Python; no network exfiltration or credential access, entirely local file-based pipeline.

⚠ 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.

8
security
100
transparency
90
maintenance

Findings (4)

Pattern match critical

Pipe to bash — executes piped content as shell commands

SKILL.md · code · | bash

Pattern match critical

Pipe to python — executes piped content as Python code

SKILL.md · code · | python3

Pattern match critical

Unicode homoglyph detected — uses lookalike characters to evade pattern matching

scripts/detect-feedback.py · prose

Pattern match low

Python os.environ.get — reads environment variable

scripts/analyze-patterns.py · prose · downgraded · os.environ.get(

Why the tier is capped

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