datadog-automation

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads Datadog logs and events which can contain outsider-submitted application logs or event text.

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

• Potentially malicious external URL detected (high risk: 0.70). The instruction references https://rube.app/mcp as an MCP server setup endpoint, which is a weak/unknown/suspicious operational dependency supplying agent connectivity and tooling configuration.