test-generator
Warn
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (MEDIUM): The skill processes untrusted source code to generate executable test suites without explicit boundary markers or sanitization. * Ingestion points: Target source files provided as arguments (e.g., UserService.js, parser.py). * Boundary markers: Absent. There are no instructions to the agent to ignore or delimit natural language instructions found within the code being analyzed. * Capability inventory: The skill facilitates the generation of code intended for file system persistence and execution (via Jest, pytest, etc.), creating a path for code injection. * Sanitization: Absent. No validation or filtering of the analyzed content is performed.
Audit Metadata