Caveat verdict

grounding

visual-grounding

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

The skill uses a multimodal grounding capability to detect objects in images, but it doesn't demonstrate any 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. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

65
security
50
transparency
70
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (1)

Pattern match high

HTTP request to bare IP address — common in malicious payloads

SKILL.md · code · http://172.20.112.202

Permissions & capabilities

No declared permissions — minimal attack surface.

credential_access

Is this flag fair?

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