ClawAudit verdict

wxclawbot-send

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

WeChat proactive message push skill using the local wxclawbot CLI with credentials from the user's existing OpenClaw WeChat login; sends only to user-specified contacts with no exfiltration.

⚠ 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.

68
security
100
transparency
100
maintenance

Findings (2)

Pattern match critical

Possible hardcoded credential

README.en.md · code · TOKEN="[email protected]:your-token

Pattern match low

Accesses sensitive environment variables

src/accounts.ts · prose · downgraded · process.env.WXCLAW_TOKEN

Permissions & capabilities

Requires 1 system binary.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API