ask-unit-test-generation
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- General Analysis (SAFE): No malicious patterns or behaviors were detected in any of the skill files. The instructions provided to the agent are consistent with its stated purpose of improving code quality and test coverage.
- Indirect Prompt Injection (LOW): The skill is designed to process untrusted source code provided by users, which is a known vector for indirect prompt injection. 1. Ingestion points: User-provided functions and classes for test generation (README.md). 2. Boundary markers: None specified in the instructions. 3. Capability inventory: Generates unit test code and advises the agent on file system placement (README.md). 4. Sanitization: No sanitization or filtering logic is present.
- Metadata Analysis (SAFE): The metadata in skill.yaml and SKILL.md is consistent with the skill's functionality. The inclusion of 'antigravity' in the agents list is noted as a likely Easter egg or placeholder and carries no functional security risk.
Audit Metadata