senior-prompt-engineer

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

• Third-party content exposure detected (high risk: 0.90). The skill's documentation and code explicitly define and use web-retrieval tools and RAG flows (e.g., the Tool Definition "search_web"/example web_search in references/agentic_system_design.md and the agent_orchestrator.py/SKILL.md RAG Evaluator which consumes retrieved contexts.json and ReAct examples calling search()), so the agent is expected to ingest open/public third-party content (web/search results or retrieved contexts) that can directly influence tool selection and subsequent actions.