prompt-engineering

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

• Third-party content exposure detected (high risk: 0.90). The skill includes RAG and web-search/agent examples that retrieve and inject external documents/search results into prompts (see references/rag-patterns.md and the ReAct web-search/prompt-chaining examples using vector_db.similarity_search and "Search results"), which means the agent is expected to read and reason over untrusted third‑party content.