testing-best-practices
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): The skill is entirely composed of natural language instructions and markdown templates for test planning.
- No Code Execution: The skill does not contain any scripts (.py, .js, .sh) or commands that interact with the host system.
- Data Privacy: While the skill instructions involve reading codebase specs and source files to generate test plans, it does not include any network calls or mechanisms to exfiltrate this data.
- No Prompt Injection: No patterns were detected that attempt to override system prompts or bypass safety filters.
- Best Practices: The skill actually enforces safety and security best practices, such as explicitly forbidding 'test-only hacks' in production code and requiring that test data be derived from actual schemas rather than being fabricated.
Audit Metadata