ClawAudit verdict
compliance-check
Runs a local Python script that checks user-supplied text against bundled word lists with no network access or credential requirements; behavior is purely local and matches the stated content compliance purpose.
⚠ 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 (6)
Pipe to python — executes piped content as Python code
scripts/check.py · prose · downgraded · | python
Possible hardcoded credential
scripts/check.py · prose · downgraded · API_KEY='):
key = line.split(
HTTP request to bare IP address — common in malicious payloads
scripts/api_server.py · prose · downgraded · http://0.0.0.0
Accesses OpenClaw config/secrets directly
scripts/check.py · prose · downgraded · ~/.openclaw/.env
Python os.environ.get — reads environment variable
scripts/api_server.py · prose · downgraded · os.environ.get(
Python urllib.request — network access
scripts/check.py · prose · downgraded · urllib.request
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.