Caveat verdict
ask-claude
ask-claude-skill
88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.
Nearly identical to ask-claude — delegates tasks to Claude Code CLI with persistent sessions confined to the user-specified workdir; no network exfiltration or secret access described.
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.
100
security
70
transparency
80
maintenance
No red flags detected in static analysis.
Checked: 115 threat patterns · AST capability extraction · cross-zone compound shapes · permission integrity.
Permissions & capabilities
No declared permissions — minimal attack surface.
data_encoding Was this verdict right?
Thanks — recorded.