ClawAudit verdict
pixiv-skill
pixiv
The skill uses a cookie for authentication and accesses Pixiv's API, which may pose security risks if the cookie is leaked or used improperly.
⚠ 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
scripts/pixiv.py · prose · downgraded · SECRET = "lsACyCD94FhDUtGTXi3QzcFE2uU1hqtDaKeqrdwj
HTTP request to bare IP address — common in malicious payloads
config.example.yaml · prose · downgraded · http://127.0.0.1
References webhook/callback URL
scripts/pixiv.py · prose · downgraded · callback_url
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.