ClawAudit verdict

ydc-ai-sdk-integration

88
๐ŸŸข Trusted
Low risk โ€” reviewed by ClawAudit, behavior matches stated purpose

Integration guide for adding You.com tools to Vercel AI SDK; credential access is for a user API key consistent with the stated SDK integration purpose.

โš  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.

45
security
50
transparency
70
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (2)

Pattern match critical

Possible hardcoded credential

SKILL.md ยท code ยท apiKey: 'your-custom-key

Pattern match medium

Accesses sensitive environment variables

SKILL.md ยท code ยท process.env.YDC_API_KEY

Permissions & capabilities

No declared permissions โ€” minimal attack surface.

network_incredential_access

Is this flag fair?

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