agentic-ai-dev

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md’s runtime workflow exposes an agent to outsider-authored free text via FastAPI user inputs (POST /invoke or /stream) that are then passed into the LangGraph agent as messages, e.g., guarded_agent_node/route patterns using request.message as the human message content.