doc-coauthoring

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

• Third-party content exposure detected (high risk: 0.90). The skill's Stage 1 instructions explicitly tell the agent to fetch and read user-provided/shared content via integrations (e.g., "If they provide a link to a shared document, use the appropriate integration to fetch it" and mentions Slack, Teams, Google Drive, SharePoint), so it will ingest user-generated third-party content and use that context to drive drafting and subsequent actions.