dependency-flow

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to call public MCP tools and CLIs that fetch data from third-party sources (e.g., maestro_latest_build/maestro_default_channels/maestro_builds against "https://github.com/dotnet/maui", darc get-asset and AzDO build summary pages) and to read/interpret those outputs to decide/promote builds, so untrusted external content can materially influence actions.