code-testing-agent
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
- Orchestrated Command Execution: The skill utilizes standard build and testing commands, such as
dotnet buildanddotnet test, to ensure that generated tests are functional and valid. These operations are essential for the skill's primary objective of providing workable unit tests. - Dynamic Code and File Management: The skill generates new test files and may modify project configuration files (like
.csprojin .NET environments) to ensure correct assembly referencing. This is a standard requirement for maintaining build integrity in complex projects. - Codebase Analysis Surface: To generate effective tests, the skill performs deep analysis of the user's source code. While this ingestion point represents a surface for indirect prompt injection from codebase comments or patterns, the skill's instructions focus on structural API analysis to minimize risks.
- State Management in Local Storage: The skill maintains its internal pipeline state (research results and implementation plans) in a local
.testagent/directory, which is a common and transparent practice for complex agentic workflows.
Audit Metadata