ClawAudit verdict
kindle-claude-monitor
The skill sets up an HTTP server to receive hooks and render an e-ink friendly dashboard, which could potentially be used for malicious purposes.
⚠ 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
agent_memory
Findings (4)
References sudo — requests elevated privileges
README.md · code · sudo
Pipe to python — executes piped content as Python code
scripts/notify.sh · prose · downgraded · | python3
Opens WebSocket connection
SKILL.md · prose · downgraded · WebSocket
Python os.environ.get — reads environment variable
scripts/server.py · prose · downgraded · os.environ.get(
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.
network_inagent_memory Is this flag fair?
Thanks — recorded.