discover-by-geography

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

• Third-party content exposure detected (high risk: 0.90). The skill's "Enumerate" procedure explicitly instructs the agent to gather and interpret information from public third-party sites (e.g., local startup directories, accelerator/VC portfolio pages, LinkedIn company filters, and conference/meetup sponsor lists), which the agent will read and use to determine hiring/contact status and subsequent actions, exposing it to untrusted user-generated web content that could carry indirect prompt injection.