miro-doc

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

• Third-party content exposure detected (high risk: 0.70). The skill's "Editing Existing Documents" workflow explicitly instructs the agent to call doc_get on a Miro document URL to read the document content and then doc_update to modify it, meaning the agent will ingest user-generated/untrusted Miro board content which could contain instructions that influence subsequent actions.