implementation-task-planner

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow instructs the agent to “Inventory source artifacts” and “Extract acceptance criteria… constraints” from provided artifacts, which at runtime may include outsider-authored free-text inputs (e.g., issue/PR/wiki/discussion bodies) that the agent reads into its LLM context to generate the plan.