ClawAudit verdict
clawguard-guardian
Runtime guardian that intercepts and logs agent operations locally with freeze/replay capabilities; behavior matches its stated security monitoring purpose with no suspicious external data flows.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
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.
Findings (7)
Accesses sensitive system files
SKILL.md · code · /etc/passwd
Recursive delete from root or home — destructive command
SKILL.md · code · rm -rf /
Bash /dev/tcp — raw TCP connection via shell
SKILL.md · code · /dev/tcp/
Pipe to sh — executes piped content as shell commands
SKILL.md · prose · downgraded · |sh
Accesses .ssh directory
SKILL.md · code · .ssh/
References sudo — requests elevated privileges
SKILL.md · prose · downgraded · sudo
Sets world-executable permissions
SKILL.md · code · chmod 777
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_store Is this flag fair?
Thanks — recorded.