ClawAudit verdict
jiuwu-agent
The skill appears to be a text or file analysis tool that uses the Jiuwu intelligent body API. It does not seem to have any malicious or deceptive 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 (5)
Possible hardcoded credential
scripts/call_agent.py · prose · downgraded · TOKEN='):
return line.split(
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/.env
HTTP request to bare IP address — common in malicious payloads
scripts/call_agent.py · prose · downgraded · http://192.168.1.213
Python urllib.request — network access
scripts/call_agent.py · prose · downgraded · urllib.request
Python os.environ.get — reads environment variable
scripts/call_agent.py · prose · downgraded · os.environ.get(
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.