Skip to content

Latest commit

 

History

7 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

RAGShield — Agentic RAG Security Research & Red-Teaming Framework

RAGShield is a security research and red-teaming framework for Retrieval-Augmented Generation pipelines. It provides an intentionally instrumented test environment with modular attack vectors (Corpus Poisoning, Indirect Prompt Injection, Tool Hijacking, Latent Backdoors) alongside defensive mitigation layers.

Defenses & Mitigations

  • Corpus Integrity Verification: Semantic hash chaining and provenance tracking on ingested knowledge chunks.
  • Perplexity & Token Anomaly Filters: Detects high-entropy injected instructions embedded in retrieved passages.
  • Tool-Call Guardrails: Validates that LLM tool invocations conform to strict schema boundaries and authorization scopes.

Usage

# Run security red-teaming benchmark against standard RAG pipeline
python main.py --benchmark --defenses active

Tests

pytest tests/ -v

About

Agentic RAG security research framework with attack vectors (corpus poisoning, tool injection) and modular defenses for red-teaming.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages