a11y-debugging

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to navigate to arbitrary web pages and fetch/inspect their content (e.g., using take_snapshot, take_screenshot, list_console_messages, Lighthouse audits, evaluate_script snippets) and even to fetch external docs like web.dev/*.md.txt, so it ingests untrusted third-party page content that can influence follow-up actions.