agentic-jumpstart-testing
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): No instructions attempting to override agent behavior or bypass safety filters were detected. The description and content are strictly instructional regarding software testing.
- [Data Exposure & Exfiltration] (SAFE): While the skill contains example credentials (e.g., 'test@example.com' and 'password'), these are explicitly used within the context of test scripts and mocks, posing no risk of real-world credential leakage. Sensitive file paths referenced (e.g., 'playwright/.auth/user.json') are standard for Playwright authentication state management.
- [Unverifiable Dependencies] (SAFE): The skill references reputable and industry-standard libraries including Vitest, Playwright, and Testing Library. No suspicious or unknown third-party packages are requested for installation.
- [Command Execution] (SAFE): The provided shell commands are standard npm scripts for running test suites (e.g., 'npm run test') and do not involve arbitrary command execution or obfuscated logic.
Audit Metadata