backend-test-writer
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION] (SAFE): The skill instructions are strictly task-oriented and do not contain any patterns intended to bypass agent guardrails or extract system prompts.
- [DATA_EXFILTRATION] (SAFE): No network operations or sensitive file accesses are performed. Hardcoded strings in examples are standard test placeholders (e.g., test@example.com).
- [EXTERNAL_DOWNLOADS] (SAFE): References to dependencies (jest, supertest, faker) point to established, trusted packages within the NPM ecosystem and are provided as recommendations for the user's development environment.
- [REMOTE_CODE_EXECUTION] (SAFE): The skill is designed to output code blocks for the user to review and run manually; it does not execute code or download remote scripts for runtime execution.
- [COMMAND_EXECUTION] (SAFE): There are no subprocess calls or shell commands integrated into the skill workflow.
Audit Metadata