ClawAudit verdict
smart-keepalive
The skill has an execution sink detected, which could potentially be used for malicious code execution.
⚠ 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 (5)
subprocess execution — runs system commands from Python
smart-keepalive.py · prose · downgraded · subprocess.run(
Accesses OpenClaw config/secrets directly
smart-keepalive.py · prose · downgraded · ~/.openclaw/openclaw.json
Python os.getenv — reads environment variable
smart-keepalive.py · prose · downgraded · os.getenv(
Python urllib.request — network access
smart-keepalive.py · prose · downgraded · urllib.request
Popular HTTP library — network access
smart-keepalive.py · prose · downgraded · got
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class 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.