docs-expert

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

• Third-party content exposure detected (high risk: 0.70). The DOC_COAUTHORING workflow explicitly instructs the agent to fetch and read user-provided shared documents and channel content via integrations (e.g., "If they provide a link to a shared document, use the appropriate integration to fetch it" and "if user mentions team channels or shared documents... use the appropriate integration" in references/DOC_COAUTHORING.md), which means the agent will ingest untrusted/user-generated third‑party content and use it to drive drafting, verification, and sub-agent tests.