meta-migration-assistant

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

• Third-party content exposure detected (high risk: 0.85). The required workflow routes to deep-research or github/multi-search-engine, which (by design) fetches authoritative migration guides from external sources at runtime; that fetched public web/repo text is then ingested into the agent’s LLM context for write_plan (indirect prompt injection risk).