aws-agentic-ai

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

• Third-party content exposure detected (high risk: 0.90). The skill includes a Browser service that explicitly navigates to arbitrary URLs and extracts page content (see services/browser/README.md "Navigation" and "Content Extraction" actions), which means the agent will fetch and read untrusted public web pages and user-provided URLs as part of its workflow.