dotnet-dev

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions to manage the development lifecycle through the dotnet CLI (e.g., dotnet ef for migrations, dotnet build, dotnet test) and utilizes npx to execute utility packages like mcporter and mcp-remote. These operations are consistent with the skill's primary purpose of providing .NET development expertise.\n- [EXTERNAL_DOWNLOADS]: Fetches documentation from the official Microsoft Learn MCP server (https://learn.microsoft.com/api/mcp). It also references well-known development dependencies from the NuGet registry and standard container images (e.g., PostgreSQL, Redis, RabbitMQ) used within .NET Aspire and integration testing contexts.\n- [PROMPT_INJECTION]: An indirect prompt injection surface is identified as the skill processes documentation retrieved from external sources.\n
  • Ingestion points: Documentation content fetched from the microsoft-learn MCP server as specified in references/microsoft-learn-mcp.md.\n
  • Boundary markers: Absent; the instructions do not implement specific delimiters or safety wrappers for the content retrieved from the MCP tool.\n
  • Capability inventory: The skill allows for subprocess execution via dotnet and npx, as well as container management via Docker/Aspire.\n
  • Sanitization: No specific filtering or validation logic is applied to the retrieved documentation content, though the risk is minimized by the use of a trusted source (Microsoft).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 03:14 AM