migrate-xunit-to-xunit-v3
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill scans and processes local project files and source code within the workspace, which creates a potential surface for indirect prompt injection if any of those files contain untrusted or adversarial content.
- Ingestion Points: Discovers and inspects
.csproj,.sln,.slnx, central package properties, and C# source files in the current working directory. - Boundary Markers: There are no explicit boundary markers or instructions instructing the model to ignore embedded prompts or code comments within the analyzed codebase.
- Capability Inventory: The skill is capable of modifying files (updating references, changing signatures) and running test suites via build system commands.
- Sanitization: Content within the discovered repository files is not explicitly validated or sanitized before handling.
Audit Metadata