msbuild
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- Command Execution: The skill provides instructions for the agent to execute build and diagnostic commands using the
dotnetandmsbuildCLI tools. These operations are necessary for investigating failures and analyzing performance in .NET projects. - Data Sensitivity Considerations: The skill contains explicit warnings regarding binary logs (
.binlog), noting that they may capture sensitive information like environment variables or credentials. It advises the agent to treat these logs as sensitive diagnostic data and to keep them local. - Defensive Authoring Guidance: The provided references include an extensive catalog of MSBuild anti-patterns (e.g., AP-01, AP-16, AP-19). These patterns educate the user and agent on avoiding unsafe practices, such as unnecessary shell execution or performing side-effecting operations during the project evaluation phase.
- Indirect Prompt Injection Surface: The skill is designed to process external inputs such as build logs and project XML files. While this creates a theoretical surface for indirect prompt injection, the skill mitigates risk by recommending structured analysis tools over raw text parsing.
Audit Metadata