ClawAudit verdict
agent-guardrails
jz-agent-guardrails
The skill installs git hooks and scripts for code enforcement, which could potentially lead to security issues if not properly configured.
⚠ 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)
Instructs covert action — may act without user awareness
SKILL.md · frontmatter · secretly
Popular HTTP library — network access
references/deployment-verification-guide.md · code · got
Uses exec() — may execute shell commands
scripts/check-secrets.sh · prose · downgraded · exec(
References child_process — can spawn system processes
scripts/check-secrets.sh · prose · downgraded · child_process
Uses spawn() — can execute external programs
scripts/check-secrets.sh · prose · downgraded · spawn(
References agent configuration files
README.md · prose · downgraded · CLAUDE.md
Python os.getenv — reads environment variable
references/agents-md-template.md · prose · downgraded · os.getenv(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/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.
Is this flag fair?
Thanks — recorded.