excalidraw-skill

Warn

Audited by Snyk on Feb 22, 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's workflows explicitly call describe_scene and GET /api/elements (see SKILL.md and references/cheatsheet.md) against a configurable EXPRESS_SERVER_URL (default http://localhost:3000) and allow using/exporting shareable excalidraw.com URLs that "anyone can open it in excalidraw.com to view and edit", so the agent will fetch and read user-generated, potentially public canvas content which can directly influence subsequent element-creation/updates and tool use.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 22, 2026, 05:00 AM