e2e-test

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

• Third-party content exposure detected (high risk: 0.90). The skill issues navigations to arbitrary URLs (see template steps with action: navigate and params: { url: ... }) and explicitly reads page content via mcp__claude-in-chrome__read_page / find (used in assertions like text_equals and element_exists), so it ingests and interprets web page content that could be untrusted third-party content.