azdo-build-investigator

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and interpret untrusted, user-generated CI data (e.g., Helix API GET https://helix.dot.net/api/... and Azure DevOps File Container API artifact downloads) as part of its required investigation workflow, and those external logs can directly influence tool use and next actions.