ClawAudit verdict

autoglm-toolkit

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

A legitimate API client toolkit for Zhipu AI services (browser automation, search, image generation) using standard API authentication; credentials are used only for the stated API calls to the provider's own endpoints.

⚠ 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.

70
security
80
transparency
90
maintenance

Findings (1)

Pattern match critical

Possible hardcoded credential

SKILL.md · frontmatter · TOKEN: "AutoGLM API token (obtained from local service or manual config)

Permissions & capabilities

No declared permissions — minimal attack surface.

data_encoding

Is this flag fair?

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