← Back to List
⚠
Notice:This resource is provided by a third-party author. Please review the code with AI tools or manually before use to ensure security and compatibility.
Pythonethz-spylab/agentdojo

agentdojo

A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.

72.6/100
★ 561Forks: 146
View on GitHub →Homepage →
Loading report...

Similar Projects

FlashRAG

77

⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)

Python★ 3.5K

llm-guard

56

The Security Toolkit for LLM Interactions

Python★ 2.9K

promptbench

58

A unified evaluation framework for large language models

Python★ 2.8K

ISC-Bench

78

Internal Safety Collapse: Turning the LLM or an AI Agent into a sensitive data generator.

Python★ 773
← Back to List