ci-analysis

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

• Third-party content exposure detected (high risk: 0.90). The skill's script and workflow explicitly fetch and parse open/public third‑party content (Azure DevOps builds at dev.azure.com, Helix logs/artifacts at helix.dot.net, GitHub PRs/issues via gh, and MihuBot search at mihubot.xyz) and instruct the agent to interpret that content (logs, issue listings, Build Analysis output) to make triage and retry decisions, so untrusted user-generated content can materially influence agent actions.