qa-reporter

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

• Third-party content exposure detected (high risk: 0.78). When Plane context is provided, the skill fetches the Plane work item and reads its title/description/comments/links/attachments (including any Notion links) into report_state, so outsider-authored free text from Plane comments/description can be ingested into the agent’s LLM context via the Plane MCP retrieval path.