skills/nvidia/skills/tao-analyze-gaps-vlm-bcq/Snyk

tao-analyze-gaps-vlm-bcq

Warn

Audited by Snyk on Aug 25, 2026

Risk Level: MEDIUM

Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

Third-party content exposure detected (medium risk: 0.30). The skill’s runtime path gap_analysis vlm_bcq reads an outsider-controlled predictions_json file (field text like response and gt parsed for yes/no) and produces FP/FN gap records from that content.

Issues (1)

W011

MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata

Risk Level

MEDIUM

Analyzed

Aug 25, 2026, 02:40 PM

Issues

1

Security Audit — snyk — tao-analyze-gaps-vlm-bcq