dotnet-inspect

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests public, user-published content (e.g., querying nuget.org with --latest-version/--versions and fetching/printing SourceLink source files via the "source ... --cat" and "source" commands) so untrusted third-party code/docs can be read and used by the agent as part of its workflow.