qa

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly accepts and pre-flights arbitrary URLs (Phase 0 Step 6: "If invoked as /qa <url>" with a curl probe) and then uses Playwright to navigate and inspect that URL (references/subagent-prompts.md "Browser Verification Sub-Agent" — "Navigate to … Check the console for errors" and related steps), which means it fetches and interprets untrusted third-party web content as part of its workflow and can change testing/agent actions based on that content.