ClawAudit verdict
xiaoyiwebsearch
The skill appears to be a legitimate search tool, with no evidence of 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.
Findings (3)
Possible hardcoded credential
search.js · prose · downgraded · TOKEN = 'eyJhbGciOiJQUzI1NiIsImtpZCI6IjNjMWZhNWQwNjIxNzRkYTA4MWNlY2E4NTY3NDViYTQ
Long base64 string (100+ chars) — likely obfuscated payload
search.js · prose · downgraded · eyJhdWQiOiJodHRwczovL29hdXRoLWxvZ2luLmNsb3VkLmh1YXdlaS5jb20vb2F1dGgyL3YzL3Rva2Vu
Popular HTTP library — network access
package-lock.json · prose · downgraded · axios
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.