scientific-slides

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs use of the "research-lookup" workflow to fetch public literature and tells the agent to list and attach user-provided files from working directories (e.g., "user-provided input files or directories" and the --attach options in generate_slide_image.py), so the agent will ingest open/public third-party content and arbitrary user-supplied images as part of its slide-generation workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 04:02 AM