ClawAudit verdict
wechat-new-tool
The skill provides a smart dispatch for WeChat sending requests, which is a legitimate use case.
⚠ 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
wechat.yaml · prose · downgraded · TOKEN: "e4cf78e3-afdf-4a45-8090-143ab4df83f2
Popular HTTP library — network access
package.json · prose · downgraded · axios
Accesses sensitive environment variables
wechat_bridge.js · prose · downgraded · process.env.WECHAT_TOKEN
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.