harness-engineering

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of documentation and configuration templates intended to improve repository health and agent reliability. It does not include malicious payloads or unauthorized access patterns.
  • [EXTERNAL_DOWNLOADS]: References industry-standard and official resources, including 'actions/checkout' and established development libraries like 'ArchUnit', 'eslint-plugin-import', and 'import-linter'. These are documented neutrally as trusted dependencies for architectural enforcement.
  • [PROMPT_INJECTION]: Provides a framework for defining explicit safety constraints and forbidden operations in an 'AGENTS.md' file. These are defensive instructions designed to reduce hallucinations and ensure agents adhere to project-specific safety protocols.
  • [COMMAND_EXECUTION]: Includes templates for maintenance scripts and CI/CD workflows, such as 'bin/test' and 'bin/gc-pr'. These tools are designed to be implemented by the user to automate quality gates and technical debt removal within their own infrastructure.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 09:04 AM