ClawAudit verdict

wecom

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

The skill is designed to send messages to WeCom. It uses legitimate capabilities such as network in and package installation and does not exhibit any malicious behavior.

⚠ 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.

75
security
50
transparency
80
maintenance

Permission integrity

Performs file operations but does not declare file-accessing binaries

file_read+write

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (2)

Pattern match medium

References webhook/callback URL

SKILL.md · code · WEBHOOK_URL

Pattern match low

Popular HTTP library — network access

dist/index.js · prose · downgraded · axios

Permissions & capabilities

No declared permissions — minimal attack surface.

network_inpackage_installfile_write

Is this flag fair?

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