why

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

• Third-party content exposure detected (high risk: 0.85). The required workflow delegates to multiple “investigators” that query external MCPs (issue trackers, long-form docs, real-time chat, observability, analytics warehouses) and then passes their findings into the synthesizer/LLM context, so outsider-authored free text from those systems can be ingested at runtime via the MCP result payloads.