ai-agents-tools

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly lists "Web search" and "REST API reader" under Knowledge Tools and the ReAct/Agent Execution Loop describes calling tools and ingesting their results, so the agent can fetch and interpret open/public web content (e.g., web pages, API responses) that could influence actions.