crewai-task-and-tool-design

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

• Third-party content exposure detected (high risk: 0.75). The workflow ingests only the approved ai-architecture.md contract and then executes a closed, adapter-mediated retrieve_sources tool whose runtime outputs are treated as retrieved source material; this is an outsider source category (public/externally fetched content) that can become LLM-readable text via the Researcher/Writer context, creating indirect prompt-injection risk.