safety-filter-bypass

Community

Test and harden AI safety filters.

Authorpluginagentmarketplace
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill enables authorized testers to assess and bypass AI safety filters and guardrails to identify weaknesses in protective mechanisms.

Core Features & Use Cases

  • Testing: Evaluate pre-filter, post-filter, and guidance robustness across LLM deployments.
  • Technique catalog: Includes encoding, semantic, structural, and multimodal bypass strategies with ready-to-run examples.
  • Ethical testing: Provides guidelines for responsible disclosure and consent-based testing in controlled environments.

Quick Start

Run authorized tests with the included harness to execute encoding and semantic bypass variants against your configured filters.

Dependency Matrix

Required Modules

None required

Components

scriptsreferencesassets

💻 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: safety-filter-bypass
Download link: https://github.com/pluginagentmarketplace/custom-plugin-ai-red-teaming/archive/main.zip#safety-filter-bypass

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 223,000+ vetted skills library on demand.