qa

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly runs Playwright against live, potentially arbitrary URLs (see "Workflow" step 2 and "Identify target" allowing /qa <url>) and inspects page content (titles, buttons, redirects, JS errors) — i.e., it fetches and interprets untrusted public web content as part of its decisioning.