Skills
.Work. You
Rest

retrieval-poisoning-test

Community

Validate model safety by testing against retrieval poison attacks.

Data & Analytics#data integrity#model security#model testing#retrieval poison attacks#RAG model
Authorjassics
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill ensures the integrity and safety of a Retrieval-Aggregated-Generative (RAG) model by identifying potential vulnerabilities to retrieval poison attacks.

Core Features & Use Cases

  • Vulnerability Testing: Detects content manipulation in a RAG corpus that can manipulate the model's answers.
  • Security Validation: Validates ingestion/retrieval trust boundaries within RAG applications.
  • Use Case: Before deploying a new RAG app, use this Skill to ensure it cannot be manipulated by attackers to provide incorrect information or trigger actions without intent.

Quick Start

To test your RAG app against retrieval poison attacks, execute 'retrieval-poisoning-test:run'.

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: retrieval-poisoning-test
Download link: https://github.com/jassics/awesome-claude-security/archive/main.zip#retrieval-poisoning-test

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 620,000+ vetted skills library on demand.