al

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

• Third-party content exposure detected (low risk: 0.10). The required workflow runs an external CLI command (npx -y alignfirst guide aad) to fetch protocol guidance and work files, which may process external content.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill fetches and executes an arbitrary npm package via npx from an unverified third-party repository locator, resulting in a high-risk unverifiable runtime external dependency.