apex

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

• Third-party content exposure detected (high risk: 0.80). The workflow (not optional examples) explicitly launches websearch and explore-docs agents in Step 01 Analyze (steps/step-01-analyze.md) to fetch and synthesize public web/docs content which the agent must read and use to drive planning and execution, exposing it to untrusted third-party content that can influence tool use and decisions.