ClawAudit verdict
方正鸿云编辑助手
founder-hy-editor-browser
The skill uses browser.evaluate() to execute API calls, which may send data to external hosts. However, it is designed for automating interactions with the Fang Zheng Hong Yun platform and has legitimate purposes.
⚠ 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.
Permission integrity
network_out
Findings (1)
Possible hardcoded credential
SKILL.md · prose · downgraded · SECRET="your_secret
Permissions & capabilities
No declared permissions — minimal attack surface.
network_outnetwork_in Is this flag fair?
Thanks — recorded.