Caveat verdict

composio-integration

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

The skill embeds a live Composio API key and a user_id directly in the skill file content, meaning any party reading this skill obtains credentials with access to the user's Gmail and Google Tasks accounts.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

65
security
50
transparency
80
maintenance

Findings (3)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="ak_AXxQjyexBuSiJXTYOTPB

Pattern match low

Node http/https module — low-level network access

scripts/test-gmail.js · prose · downgraded · require('https')

Pattern match low

Accesses sensitive environment variables

scripts/test-gmail.js · prose · downgraded · process.env.COMPOSIO_API_KEY

Permissions & capabilities

No declared permissions — minimal attack surface.

credential_access

Is this flag fair?

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