ClawAudit verdict

1688-distribution

45
🟠 Risky
Significant concerns — only install if you understand the risks

The skill interacts with external services and handles user credentials, but its behavior seems to be primarily functional and transparent, though some operations like handling AK (Access Key) could be considered risky if not properly secured.

⚠ 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.

45
security
90
transparency
70
maintenance

Findings (6)

Pattern match high

<script> tag in markdown — potential code injection

scripts/_sys/_callback_server.py · prose · downgraded · <script>

Pattern match medium

subprocess execution — runs system commands from Python

scripts/_sys/_ak_crypto.py · prose · downgraded · subprocess.run(

Pattern match medium

Accesses OpenClaw config/secrets directly

scripts/_sys/_auth.py · prose · downgraded · ~/.openclaw/openclaw.json

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

scripts/_sys/_callback_server.py · prose · downgraded · http://127.0.0.1

Pattern match low

Python os.environ.get — reads environment variable

scripts/_sys/_const.py · prose · downgraded · os.environ.get(

Pattern match low

importlib.import_module — dynamic module loading

scripts/cli.py · prose · downgraded · importlib.import_module(

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 1 system binary.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API