Caveat verdict

Vision Sandbox

vision-sandbox

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

Vision analysis skill using Gemini code execution sandbox for spatial grounding and UI auditing; sends images to Google API which is explicitly stated and expected for this use case.

⚠ 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.

68
security
100
transparency
90
maintenance

Findings (2)

Pattern match critical

Possible hardcoded credential

AGENTS.md · code · API_KEY="your_api_key_here

Pattern match low

Python os.getenv — reads environment variable

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

Permissions & capabilities

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

Is this flag fair?

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