migrate-project

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

• Third-party content exposure detected (high risk: 0.75). The runtime LLM context is populated by the orchestrator dispatch prompts to Agent specialists, and those prompts include target-map.md / plan.md / per-slice slice scope read from the outsider-authored target repository (user did not author those markdown files), which are free-form text that can contain indirect prompt-injection payloads.