linear-implement

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

• Third-party content exposure detected (high risk: 0.75). The required workflow reads the newest Linear “marked plan” comment (outsider-authored issue/comment text) and re-reads its open_questions/accepted_unknowns/do_not_assume to drive implementation, so that free-form content can enter the agent’s LLM context via the Linear MCP get_issue/list_comments → plan parsing path.