Caveat verdict

halucatch

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

AI Skill reliability auditor that reads skill folder files and runs local Python scripts for quality checks; a defensive engineering tool with no suspicious network or exfiltration behavior.

⚠ 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.

38
security
90
transparency
90
maintenance

Findings (4)

Pattern match critical

Attempts to modify skills or system prompts

README.en.md · code · Edit SKILL.md

Pattern match high

Writes to SKILL.md — self-modifying skill

README.en.md · prose · downgraded · SKILL.md](SKILL.md) append

Pattern match medium

Instructs covert action — may act without user awareness

halucatch_core.py · prose · downgraded · silently

Pattern match low

Popular HTTP library — network access

README.en.md · prose · downgraded · got

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