auth-flow-audit

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime path uses mcp__playwright__browser_navigate to load a user-supplied URL (e.g., https://...), then ingests the resulting page content via browser_snapshot/browser_evaluate/browser_network_requests, which can include outsider-authored free text from that fetched web page.