autoresearch-compliance-hardener
OfficialHarden guardrails with adversarial tests.
AuthorMINT-IA
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Automates adversarial testing to uncover weaknesses in MINT's guardrails and measure compliance risk.
Core Features & Use Cases
- Generates targeted adversarial tests to probe compliance boundaries, recording outcomes and guiding guard improvements.
- Enforces strict budgets per batch, multi-language coverage, and a repeatable improvement loop until full compliance.
- Integrates with Flutter tests and pytest for verification, and logs experiments for traceability.
Quick Start
Invoke the skill using /autoresearch-compliance-hardener (or /autoresearch-compliance-hardener 50) to start the adversarial compliance hardening workflow.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: autoresearch-compliance-hardener Download link: https://github.com/MINT-IA/MINT/archive/main.zip#autoresearch-compliance-hardener Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.