NYC

ts-testing

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • PROMPT_INJECTION (SAFE): No instructions to override safety filters or bypass constraints were found. Natural instructional language is used throughout.
  • DATA_EXFILTRATION (SAFE): No attempts to access sensitive system files or exfiltrate data to external domains were detected. The skill only interacts with project-related files like package.json and config files.
  • EXTERNAL_DOWNLOADS (SAFE): While the skill suggests installing testing libraries, it recommends standard, well-known packages from the npm registry (e.g., Vitest, Jest, Playwright).
  • REMOTE_CODE_EXECUTION (SAFE): No patterns for remote script execution or dynamic code execution were found.
  • INDIRECT_PROMPT_INJECTION (LOW): The skill has an attack surface for indirect prompt injection. 1. Ingestion points: reads package.json and config files. 2. Boundary markers: None specified. 3. Capability inventory: Writes test files and suggests running npm/npx test commands. 4. Sanitization: None specified. While the surface exists, the instructions are limited to generating standard testing boilerplate.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:06 PM