ClawAudit verdict
agent-zero
The skill provides a clear description of its functionality and requirements. It interacts with local services and uses environment variables for credentials, with no evidence of malicious behavior.
⚠ 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 (3)
Accesses system credential store
SKILL.md · frontmatter · keychain
HTTP request to bare IP address — common in malicious payloads
CLAUDE.md · prose · downgraded · http://127.0.0.1
Instructs covert action — may act without user awareness
README.md · prose · downgraded · quietly
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 6 system binaries. (2 elevated: cargo, npm).
Is this flag fair?
Thanks — recorded.