excalidraw-diagram

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md Research Mandate explicitly requires the agent to "look up the actual JSON/data formats" and "find the real event names, method names, or API endpoints" (i.e., fetch public specs/webpages) — and the rendering template also pulls a module from https://esm.sh — meaning the agent is expected to ingest open/public third‑party content that can materially influence its generation and subsequent actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The render_template.html used at runtime by references/render_excalidraw.py performs a dynamic import from https://esm.sh/@excalidraw/excalidraw?bundle which causes the agent's renderer to fetch and execute remote JavaScript during rendering, and the skill requires that import to render diagrams.