dotnet
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted repository files to detect the project stack, creating a surface for indirect prompt injection.
- Ingestion points: Repository metadata and content including
*.csproj,global.json,appsettings.json, andNuGet.configas defined inreferences/detection.md. - Boundary markers: The instructions do not specify explicit delimiters or "ignore instructions" wrappers for the ingested repository content.
- Capability inventory: The skill is authorized to run build, test, lint, and validation commands (e.g.,
dotnet test,dotnet new) which could be influenced by malicious content in the scanned files. - Sanitization: No explicit validation or sanitization of the project-level data is described before it influences the agent's command generation.
- [COMMAND_EXECUTION]: The skill is designed to invoke standard .NET CLI tools and repository-specific runners for validation and project setup.
Audit Metadata