aro-kusto

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

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches external debugging guides from GitHub repositories (Azure/ARO-HCP and Azure/ARO-RP), exposing the agent to untrusted external content at runtime.

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 fetch external debugging guides from raw.githubusercontent.com if not checked out locally, representing an unofficial runtime operational dependency.