web-perf

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

• Third-party content exposure detected (high risk: 0.75). The workflow’s runtime path includes loading a user-supplied target URL via navigate_page(url: "<target-url>") and then ingesting the resulting page/trace-derived text (e.g., insights and network request details) into the agent’s LLM context; if the target page is outsider-authored, this is an indirect prompt-injection exposure via public web content.