test-generation
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown instructions, usage examples, and code templates. No executable scripts (Python, JavaScript, Bash) or binary files are included in the package.\n- [PROMPT_INJECTION]: The skill operates by analyzing user-provided source code, which introduces a surface for indirect prompt injection if the analyzed files contain malicious instructions. However, this is an inherent aspect of the skill's primary function (code analysis) and no malicious bypasses were detected in the skill's own instructions.\n
- Ingestion points: User-provided source code files specified in commands such as '/test src/utils/calculator.js'.\n
- Boundary markers: None specified; the skill does not explicitly define delimiters to separate user code from agent instructions.\n
- Capability inventory: The skill implies the agent will read local source files and generate/write new test files.\n
- Sanitization: No sanitization or validation of the input source code is mentioned in the skill documentation.
Audit Metadata