ai-safety-redteaming

Community

Audit AI features for safety and risk.

AuthorXiaoPuOuO
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Red-team AI features, agents, and tool-enabled workflows to uncover safety failures before release or after changes.

Core Features & Use Cases

  • SOP-driven red-teaming framework for systematic safety testing
  • Coverage of prompt injection, data leakage, unsafe tool use, policy bypass, and privilege abuse
  • Structured findings, severity ratings, mitigation recommendations, and regression retests

Quick Start

Invoke the ai-safety-redteaming SOP to aggressively test AI features for safety failures and generate actionable mitigations.

Dependency Matrix

Required Modules

None required

Components

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: ai-safety-redteaming
Download link: https://github.com/XiaoPuOuO/VFactory/archive/main.zip#ai-safety-redteaming

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.