archunitnet

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches the ArchUnitNET library and its framework-specific extensions from NuGet. These resources originate from TNG Technology Consulting, a well-known and reputable organization.\n- [COMMAND_EXECUTION]: The workflow utilizes standard development tools, including the dotnet CLI for package management and test execution, and rg for repository inspection.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing external configuration files from the repository.\n
  • Ingestion points: Reads instructions and scope from the local AGENTS.md file and analyzes project structure from .csproj files.\n
  • Boundary markers: No explicit delimiters are used to isolate untrusted content in the prompt.\n
  • Capability inventory: The agent can modify project dependencies and run arbitrary test code through the dotnet toolchain.\n
  • Sanitization: No validation or escaping is applied to the content retrieved from repository files.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 07:13 PM
Security Audit — agent-trust-hub — archunitnet