ClawAudit verdict
wechat-automation
wechat-automation-api
Local desktop UI automation skill that sends WeChat messages via a Python CLI script using simulated keyboard/window control; no credentials accessed and no data sent to external hosts.
⚠ 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 (3)
Possible hardcoded credential
README_部署完成.md · code · token = "B3S6GiMbIPW1nX4VrK8JTkuEhoFcON9t
Pipe to python — executes piped content as Python code
README_完成.md · prose · downgraded · | Python
HTTP request to bare IP address — common in malicious payloads
README_部署完成.md · code · http://127.0.0.1
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
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.