supaguard

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly instructs the agent to include and test a production URL by generating and running Playwright scripts against the target site (see SKILL.md: Workflow steps 3 and 7, Constraints item 11, and the Playwright/gotchas guidance about cookie banners), which means the agent will fetch and interpret untrusted public website content that can change script logic and subsequent actions.