Caveat verdict
acp-harness-delegation
88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.
The skill appears to provide a standard protocol for delegating tasks to ACP-enabled harnesses like Claude Code or Codex, with clear documentation of triggers, core invocation methods, and prerequisites. No malicious or deceptive behavior is evident.
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
60
transparency
70
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.
process_execdata_encodingcredential_access Was this verdict right?
Thanks — recorded.