harness-creator

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill primarily serves as a knowledge base and template provider. The analyzed files consist of technical documentation, JSON templates for project tracking, and shell script templates for standard development workflows. No obfuscation, data exfiltration, or unauthorized access patterns were detected.
  • [EXTERNAL_DOWNLOADS]: The skill's init.sh template includes npm install, which is the standard method for initializing Node.js projects. This operation targets official registries and is consistent with the skill's stated purpose of setting up developer environments.
  • [COMMAND_EXECUTION]: Templates provided by the skill include common CLI commands like npm test, npm run build, and git log. These are intended to be executed by agents to verify project health and track progress as part of the harness framework.
  • [PROMPT_INJECTION]: The skill instructions do not contain any bypass markers, safety override attempts, or role-play injections. The triggers and guidance are focused on assisting the user with structured harness design.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 08:12 AM