ClawAudit verdict
uandai-ai
Uandai platform integration skill for workspace packaging and agent management using user-provided API key; all operations are standard platform automation matching the stated 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 (5)
Possible hardcoded credential
SKILL.md · code · apiKey: "uand_live_…
HTTP request to bare IP address — common in malicious payloads
references/programmatic-api.md · code · http://127.0.0.1
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json
Dynamic import() — loads module at runtime
references/programmatic-api.md · prose · downgraded · import (`
Opens WebSocket connection
references/programmatic-api.md · prose · downgraded · WebSocket
Permissions & capabilities
Requires 3 environment variables. (1 sensitive: UANDAI_API_KEY).
credential_access Is this flag fair?
Thanks — recorded.