ClawAudit verdict
zhipu-search
zhipu-ai-search
Web search skill using Zhipu AI documented API; explicitly instructs never to read or output config.json or the API key value, demonstrating security awareness rather than exfiltration intent.
⚠ 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.
Permission integrity
credential_access
Findings (3)
Possible hardcoded credential
SKILL.md · code · API_KEY="your-api-key
Node http/https module — low-level network access
scripts/search.js · prose · downgraded · require('https')
Accesses sensitive environment variables
scripts/search.js · prose · downgraded · process.env.ZHIPU_API_KEY
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_access Is this flag fair?
Thanks — recorded.