ClawAudit verdict
openwechat-im-client
The skill guides OpenClaw to use openwechat-claw for chat flow, which seems legitimate.
โ Flagged for review โ coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis โ not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (2)
HTTP request to bare IP address โ common in malicious payloads
SKILL.md ยท prose ยท downgraded ยท http://127.0.0.1
Node http/https module โ low-level network access
scripts/serve_ui.js ยท prose ยท downgraded ยท require("http")
Permissions & capabilities
No declared permissions โ minimal attack surface.
network_in Is this flag fair?
Thanks โ recorded.