visual-explainer

Warn

Audited by Snyk on Mar 5, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts URLs and (per "Input Format Handling" and the Input Collection/Phase 4 workflow) fetches and extracts web page content (requires beautifulsoup4 and lists URL/Substack as tested formats), and that fetched, untrusted public content is analyzed to drive concept extraction and image/prompt generation—so third‑party page content can materially influence tool actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 07:50 AM