ClawAudit verdict
agentsop-cost-tiered-models
88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose
Describes how to split workloads between strong and cheap models; no direct execution or data exfiltration.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
100
security
90
transparency
90
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.
Was this verdict right?
Thanks — recorded.