confluence

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly fetches and ingests user-generated Confluence content (e.g., via mcp__atlassian-evinova__confluence_search, confluence_get_page, confluence_get_comments and scripts like scripts/download_confluence.py / upload_confluence_v2.py using .mcp.json/.env-configured Confluence instances), so the agent will read and interpret third-party, user-provided pages and comments as part of its workflow.