dotnet-breaking-changes
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- Command Execution: The skill provides templates for using standard development utilities like git, grep, and the .NET CLI to automate repository inspection and build verification. These tools are used within their intended scope for software development tasks.
- Data Access: The instructions involve reading project-specific files, such as C# source files and build configurations, to understand the application's public API surface. This access is restricted to the local workspace and is necessary for the skill's functionality.
- Indirect Prompt Injection Surface: The skill ingests untrusted code and configuration files (e.g., .cs, .csproj, PublicAPI.txt) to perform its analysis. While it lacks explicit boundary markers or sanitization for these inputs, it maintains a restricted set of capabilities limited to local build and inspection tools (git, grep, dotnet CLI), and includes instructions for the agent to stop and escalate if compatibility cannot be verified.
Audit Metadata