dotnet-api-surface-validation

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and installs official tools from trusted sources.
  • Installs the Microsoft.CodeAnalysis.PublicApiAnalyzers NuGet package for build-time diagnostics.
  • References the Microsoft.DotNet.ApiCompat.Tool for baseline assembly comparison.
  • Uses official GitHub Actions such as actions/checkout@v4 and actions/setup-dotnet@v4.
  • [COMMAND_EXECUTION]: Provides implementation examples for GitHub Actions and local development that use standard CLI tools.
  • Includes standard dotnet build, dotnet pack, and dotnet tool install commands for library management.
  • Uses the GitHub CLI (gh pr edit) with the managed ${{ secrets.GITHUB_TOKEN }} for automated pull request labeling.
  • [PROMPT_INJECTION]: Contains a vulnerability surface for indirect prompt injection within the assembly reflection helper.
  • Ingestion points: The PublicApiExtractor class in SKILL.md ingests untrusted data from compiled assemblies using assembly.GetTypes() and type.GetMembers().
  • Boundary markers: The resulting API surface string is generated without delimiters or explicit instructions to the AI agent to ignore instructions embedded in type or member names.
  • Capability inventory: The skill provides instructions for build automation and package validation but does not execute logic derived directly from the reflected strings.
  • Sanitization: There is no sanitization or character filtering applied to the names of reflected types, methods, or properties before they are added to the output buffer.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 03:43 PM