qa-ui

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts user-specified URLs via $ARGUMENTS and the required workflow/Agent (SKILL.md Step "$ARGUMENTS が指定された場合" and agents/ui-evaluator allowed tools) navigates to and inspects those pages with mcp__chrome-devtools-direct__navigate_page / take_snapshot / list_console_messages, so it will fetch and interpret arbitrary third-party web content that could contain untrusted instructions.