Caveat verdict

china-vision

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

Image understanding skill that sends images to SiliconFlow Qwen2.5-VL API for scene analysis and description — sending image data to the configured vision API is the disclosed and expected core behavior.

⚠ 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.

65
security
90
transparency
90
maintenance

Findings (3)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY='sk-xxxxxxxx

Pattern match low

Python urllib.request — network access

scripts/vision.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

scripts/vision.py · prose · downgraded · os.environ.get(

Permissions & capabilities

Requires 1 environment variable. (1 sensitive: SILICONFLOW_API_KEY). Requires 1 system binary.

credential_access

Is this flag fair?

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