ai-agent-prd

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

• Third-party content exposure detected (high risk: 0.80). The skill's RAG/Knowledge sections explicitly list "web" as a knowledge source and the references (e.g., references/agent-patterns.md and references/conversation-design.md) include tools like "web_search"/"search_tool", indicating the agent is expected to retrieve and interpret content from open/public web sources.