ClawAudit verdict
Canary Agent Safety Tripwire System
canary-sr
Agent safety monitoring library that checks file paths and commands before execution, creates honeypot tripwires, and logs violations locally; all behavior matches the stated safety tripwire purpose with no exfiltration.
⚠ 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.
Permission integrity
credential_access
Findings (9)
Recursive delete from root or home — destructive command
SKILL.md · code · rm -rf /
Pipe to sh — executes piped content as shell commands
LIMITATIONS.md · code · | sh
Accesses sensitive system files
SKILL.md · code · /etc/passwd
Accesses .ssh directory
SKILL.md · code · .ssh/
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
SKILL.md · prose · downgraded · curl | sh
Accesses cloud provider credentials
SKILL.md · code · ~/.aws
subprocess execution — runs system commands from Python
SKILL.md · code · subprocess.run(
Sets world-executable permissions
SKILL.md · code · chmod 777
POSTs data to external URL
LIMITATIONS.md · code · .post('https://
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/D/F). 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_accesscredential_storefile_readprocess_exec Is this flag fair?
Thanks — recorded.