ClawAudit verdict
yeeth-claw
Supply chain security hook that intercepts package install commands and optionally submits blocked packages to a declared Argus API; credential_access is for reading the configured API key, and agent_memory is for hook registration — both match the stated security purpose.
⚠ 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
agent_memory
Findings (4)
pip3 install — installs Python packages at runtime
hooks/openclaw/hook.py · prose · downgraded · pip3 install
Python os.environ.get — reads environment variable
hooks/openclaw/hook.py · prose · downgraded · os.environ.get(
Python urllib.request — network access
hooks/openclaw/lib/argus.py · prose · downgraded · urllib.request
Popular HTTP library — network access
hooks/openclaw/lib/typosquat.py · prose · downgraded · axios
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
No declared permissions — minimal attack surface.
credential_accessagent_memory Is this flag fair?
Thanks — recorded.