vision-analysis

Warn

Audited by Snyk on Aug 15, 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). Vision analysis reads user-provided frame images from the extracted workspace frames directory, and the agent workflow then performs agent-side free-text ingestion from those images to produce per-frame on_screen_text JSON (frames/batch → agent analysis → merged reports).

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 15, 2026, 03:49 PM
Issues
1
Security Audit — snyk — vision-analysis