dogfood

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly requires navigating to and analyzing a user-provided Target URL (see Inputs and Phase 2 browser_navigate/browser_snapshot/browser_vision/browser_console), so the agent will fetch and interpret arbitrary public web content that can drive subsequent clicks and actions, enabling indirect prompt injection.