triage-issues

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads outsider-authored GitHub issue title/body/comments from microsoft/fluentui (queue items matched by gh issue list ... --json ... body,comments) and then uses that text for classification at runtime.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly runs "npx -y @playwright/cli@0.1.1" at runtime (e.g., "npx -y @playwright/cli@0.1.1 "), which downloads and executes remote npm package code, so this is a runtime external dependency that executes remote code.