ClawAudit verdict
warden-governance
an2b-warden-governance
A governance and audit skill that intercepts agent actions via before/after hooks and logs them to a local SQLite audit trail; optional enterprise API keys are clearly marked optional and the community mode works with zero cloud dependencies, consistent with a transparent policy-enforcement tool.
⚠ 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
package_install
Findings (5)
Possible hardcoded credential
UPGRADE.md · code · API_KEY: "snos_your_key_here
Recursive delete from root or home — destructive command
tests/test_skill.py · prose · downgraded · rm -rf /
os.system/popen — direct OS command execution
tests/test_skill.py · prose · downgraded · os.system(
Popular HTTP library — network access
tests/test_full_pipeline.py · prose · downgraded · got
Python os.environ.get — reads environment variable
warden_governance/settings.py · prose · downgraded · os.environ.get(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). 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.
package_install Is this flag fair?
Thanks — recorded.