ClawAudit verdict
wakehook
Integrates Google Health sleep data with an agent webhook to trigger morning routines; all connections are to the explicitly documented Google Health API and the user own agent webhook endpoint.
⚠ 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
network_out
Findings (4)
Possible hardcoded credential
SKILL.md · code · token: "<HOOKS_TOKEN>
Uses exec() — may execute shell commands
src/db.ts · prose · downgraded · exec(
HTTP request to bare IP address — common in malicious payloads
test/fanout.test.ts · prose · downgraded · http://127.0.0.1
queueMicrotask — defers execution via microtask queue
src/server.ts · prose · downgraded · queueMicrotask(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A). 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.
network_innetwork_out Is this flag fair?
Thanks — recorded.