midscene-runner
Warn
Audited by Snyk on Mar 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's execution workflow explicitly navigates to arbitrary web URLs (see the "web: url" YAML field and the "执行" / "直接使用 Midscene CLI" sections that run npx @midscene/web or Playwright/Puppeteer) and uses AI-driven steps like aiQuery/aiAssert to read and act on page content, meaning untrusted third-party webpages can be ingested and influence agent actions.
Audit Metadata