Tldraw

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

• Third-party content exposure detected (low risk: 0.10). In the required runtime workflow, the agent only reads outsider-provided free text when it is embedded in a user-supplied .tldr file passed to Tldr.ts inspect (StructureCanvas) or as --spec JSON array passed to Tldr.ts add (SketchDiagram), and the workflow does not ingest any outsider-authored text from external feeds/queues/doc sources by itself.