Caveat verdict

wechat-cover

wechat-cover-generator

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Fetches trending cover image data from a named third-party API (redfox.hk) and uses AI image analysis to generate cover design reports; API key usage is standard and explicitly documented.

⚠ 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.

58
security
100
transparency
90
maintenance

Findings (3)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="ak_xxxx...

Pattern match medium

Accesses OpenClaw config/secrets directly

SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json

Pattern match low

Python os.getenv — reads environment variable

scripts/fetch_explosive_covers.py · prose · downgraded · os.getenv(

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

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