backend-testing

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious commands, data exfiltration patterns, or obfuscation techniques were identified within the skill files. The skill correctly recommends using environment variables for sensitive data like API keys.
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection because it processes user-provided framework names and testing targets to generate code and shell commands. This is a standard characteristic of code-generation skills.
  • Ingestion points: SKILL.md (Input Format section) where users provide the '프레임워크' (Framework) and '테스트 대상' (Target).
  • Boundary markers: Absent from instructions.
  • Capability inventory: Generates shell installation commands (npm install) and configuration files (jest.config.js).
  • Sanitization: Not explicitly implemented in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 05:51 AM
Security Audit — agent-trust-hub — backend-testing