aws-ai-ml

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

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches live AWS documentation pages over the web via HTTP to read evaluation dataset schemas.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to install external packages via an npm command (npx skills add mlflow/skills --all), creating an inbound operational dependency on an unverified third-party repository/package manager.