ClawAudit verdict
ask-claude
88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose
Delegates tasks to Claude Code CLI within a user-specified workspace directory; explicitly states no access to ~/.ssh, ~/.aws, or external exfiltration, and the --bypassPermissions flag is for the local sub-agent only within the constrained workdir.
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
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.
data_encoding Was this verdict right?
Thanks — recorded.