browser-visible

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md workflow explicitly instructs starting a headed browser and opening arbitrary URLs (e.g., step 2: {"action": "open", "url": "https://example.com"}) and taking snapshots/clicking/typing, which means the agent will fetch and interpret untrusted public web content that could contain instructions influencing its actions.