tech-docs-guide

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

• Third-party content exposure detected (high risk: 0.90). Flagged because Step 2.1 explicitly instructs the agent to "通过 web fetch 最新的相关信息验证内容准确性和时效性", meaning the agent will fetch and read content from the open web (untrusted third-party sources) as part of its workflow.