Alternatives and similar repositories for prompt-injection

Users that are interested in prompt-injection are comparing it to the libraries listed below

• invariantlabs-ai / explorer
  A better way of testing, inspecting, and analyzing AI Agent traces.
  ☆35Updated last week
• llm-platform-security / SecGPT
  An Execution Isolation Architecture for LLM-Based Agentic Systems
  ☆79Updated 3 months ago
• XHMY / AutoDefense
  AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
  ☆45Updated 11 months ago
• liu00222 / Open-Prompt-Injection
  This repository provides a benchmark for prompt Injection attacks and defenses
  ☆196Updated 2 weeks ago
• haizelabs / sphynx
  Sphynx Hallucination Induction
  ☆54Updated 3 months ago
• uiuc-kang-lab / InjecAgent
  ☆62Updated 10 months ago
• PropsAI / agentserve
  A framework for hosting and scaling AI agents.
  ☆34Updated 5 months ago
• docqai / docq
  Private ChatGPT/Perplexity. Securely unlocks knowledge from confidential business information.
  ☆64Updated 7 months ago
• microsoft / TaskTracker
  TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…
  ☆55Updated 2 months ago
• hwchase17 / langfuzz
  ☆72Updated 6 months ago
• onepointconsulting / elasticsearch-agent
  ElasticSearch agent based on ElasticSearch, LangChain and ChatGPT 4
  ☆47Updated last year
• microsoft / CodePlan
  Data and evaluation scripts for "CodePlan: Repository-level Coding using LLMs and Planning", FSE 2024
  ☆68Updated 8 months ago
• FanaHOVA / openai-o1-code-interpreter
  Code interpreter support for o1
  ☆32Updated 8 months ago
• sherdencooper / GPTFuzz
  Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
  ☆488Updated 7 months ago
• AIM-Intelligence / Automated-Multi-Turn-Jailbreaks
  ☆62Updated 5 months ago
• lypsoty112 / Prompt-builder
  Prompt Builder is a small Python application that implements the principles outlined in the paper "Principled Instructions Are All You Ne…
  ☆31Updated last year
• andyzorigin / cybench
  ☆100Updated 2 months ago
• eth-sri / ToolFuzz
  ToolFuzz is a fuzzing framework designed to test your LLM Agent tools.
  ☆17Updated 2 months ago
• lakeraai / chainguard
  Guard your LangChain applications against prompt injection with Lakera ChainGuard.
  ☆22Updated 2 months ago
• All-Hands-AI / openhands-aci
  Agent computer interface for AI software engineer.
  ☆73Updated this week
• ethz-spylab / agentdojo
  A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
  ☆154Updated last week
• OS-Copilot / FRIDAY-Gizmos
  ☆28Updated last year
• DeepSoftwareAnalytics / Awesome-Agent4SE
  ☆93Updated 8 months ago
• yueqis / API-Based-Agent
  ☆50Updated 5 months ago
• agencyenterprise / PromptInject
  PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to a…
  ☆365Updated last year
• luo-anthony / DeveloperGPT
  DeveloperGPT is a LLM-powered command line tool that enables natural language to terminal commands and in-terminal chat.
  ☆43Updated 5 months ago
• unclecode / promptuner
  𝙏𝙪𝙧𝙣𝙞𝙣𝙜 𝙨𝙢𝙖𝙡𝙡 𝙩𝙖𝙨𝙠 𝙙𝙚𝙨𝙘𝙧𝙞𝙥𝙩𝙞𝙤𝙣𝙨 𝙞𝙣𝙩𝙤 𝙢𝙚𝙜𝙖 𝙥𝙧𝙤𝙢𝙥𝙩𝙨 𝙖𝙪𝙩𝙤𝙢𝙖𝙜𝙞𝙘𝙖𝙡𝙡𝙮.
  ☆79Updated 9 months ago
• brunocapelao / miniAutoGen
  Lightweight and Flexible Library for Creating Agents and Multi-Agent Conversations 🤖
  ☆24Updated last year
• controllability / jailbreak-evaluation
  The jailbreak-evaluation is an easy-to-use Python package for language model jailbreak evaluation.
  ☆23Updated 6 months ago
• egozverev / Should-It-Be-Executed-Or-Processed
  Accompanying code and SEP dataset for the "Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?" paper.
  ☆52Updated 2 months ago