excalidraw-diagram

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md's "Research Mandate" and technical-diagram requirements explicitly instruct the agent to "look up the actual JSON/data formats" and "find the real event names" from external specs/public websites and to include evidence artifacts from those sources, so the agent is expected to fetch and interpret open/public third-party content (web docs/pages) which can directly change its outputs and subsequent actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's render_template.html loads and executes remote JavaScript at runtime from https://esm.sh/@excalidraw/excalidraw?bundle (fetched by the headless browser during the render pipeline), which is a required runtime dependency that executes remote code for rendering.