diagram-quality

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow instructs the agent to invoke MCP tools (design_create, diagram_upsert, design_feedback, design_export) and process human feedback (annotations and chat messages) submitted via the agent-uml collaborative canvas, introducing indirect prompt injection risk from user-authored text.