vision-skills

Warn

Audited by Snyk on Aug 18, 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). In scripts/long_screenshot_ocr.py, the runtime calls glance ... --ocr/--query <prompt> and directly ingests the OCR/transcription output (from the screenshot chunks) as free text for subsequent Markdown merging, so outsider-authored visible text in a user-provided screenshot is LLM-ingested.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 18, 2026, 11:31 AM
Issues
1
Security Audit — snyk — vision-skills