prompt-regression-tester
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill processes test case data that can contain instructions designed to manipulate the comparison results or LLM behavior.
- Ingestion points: Data entering through the test_cases JSON structure.
- Boundary markers: None; untrusted content is directly formatted into the prompt string.
- Capability inventory: Performs LLM generation and evaluation based on processed inputs.
- Sanitization: No escaping or validation of test case fields before prompt interpolation.
Audit Metadata