excalidraw-mcp-drawing

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill explicitly requires asking the user for an Excalidraw collab URL (which contains a secret key) and then using it to call connect, which forces the agent to include that secret URL verbatim in a tool call/command — a direct secret-handling/exfiltration pattern.

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

• Third-party content exposure detected (high risk: 0.90). The skill requires the agent to connect to a user-provided Excalidraw collab URL (https://excalidraw.com/#room=...) and explicitly mandates calling get_scene first to read the canvas contents (SKILL.md "Ensure a connection first" and "Always call get_scene first"), meaning the agent will fetch and interpret arbitrary, user-generated third-party canvas data that can affect drawing decisions.