redis-excalidraw-diagrams

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

• Third-party content exposure detected (high risk: 0.70). The skill's required workflow explicitly instructs the agent to "verify Redis-specific facts in current Redis docs or the user's source material before drawing" (SKILL.md step 2) and the references file lists public redis.io URLs (references/redis-architecture-patterns.md), and the renderer template also imports runtime code from the external CDN esm.sh (references/render_template.html), so the agent is expected to fetch and act on open/public third‑party content that could influence decisions.

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

• Potentially malicious external URL detected (high risk: 0.80). The rendering template (references/render_template.html) performs a runtime ES module import from https://esm.sh/@excalidraw/excalidraw@0.18.0?bundle which is fetched and executed in the headless browser during render, and this external JS is required for the skill to render diagrams.