ClawAudit verdict
OpenClaw Gateway Guardian
gateway-guardian-zx
The skill monitors and auto-restarts the OpenClaw Gateway. While generally safe, improper use could lead to unintended behavior.
⚠ 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 (4)
References webhook/callback URL
SKILL.md · code · webhookUrl
subprocess with shell=True — command injection vector
scripts/watchdog_simple.py · prose · downgraded · subprocess.Popen(
["openclaw", "gateway", "start"],
cwd=
Python urllib.request — network access
scripts/watchdog_simple.py · prose · downgraded · urllib.request
Python os.environ.get — reads environment variable
scripts/watchdog_simple.py · prose · downgraded · os.environ.get(
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
Requires 2 system binaries.
network_in Is this flag fair?
Thanks — recorded.