Caveat verdict

deep-search-m

deep-search-mpro

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

Professional research report skill that uses agent built-in web_search and web_fetch (no external API key) to produce consulting-style reports; all behavior matches the stated multi-domain research and report generation 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.

70
security
90
transparency
90
maintenance

Findings (1)

Pattern match critical

Pipe to python — executes piped content as Python code

references/technical/integration-guide.md · code · |python

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