generate-testability-wrappers
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted code to perform its core function.
- Ingestion points: The skill reads C# source code and .csproj file contents (Static category and Target framework) provided by the user to identify static dependencies.
- Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions that might be embedded in comments within the analyzed source code.
- Capability inventory: The skill generates code for interfaces, implementations, and DI registrations which the agent is expected to write to the user's filesystem.
- Sanitization: No explicit logic is provided to sanitize or escape the input source code before it influences the generated output or logic.
Audit Metadata