product-manager

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to "Research online" and to "use search_web/read_url_content" (see the Process Flow, Behavior, and Meticulous Mode sections in SKILL.md), meaning it fetches open web content that the agent will read and use to write BRDs and drive follow-up actions — exposing it to untrusted third-party content that can influence behavior.