test-driven-development

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFE
Full Analysis
  • [Prompt Injection] (SAFE): No instructions to bypass safety filters or ignore system prompts were identified.
  • [Data Exfiltration] (SAFE): No evidence of network requests, hardcoded credentials, or access to sensitive local files.
  • [Remote Code Execution] (SAFE): No commands to download and execute external scripts.
  • [Indirect Prompt Injection] (SAFE): The skill describes running npm test on user-provided files. This is the primary skill purpose and within standard agent-user development workflow. Ingestion points: local test and source files; Boundary markers: absent; Capability inventory: shell execution of npm test; Sanitization: absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 06:05 AM