by ReversecLabs · AI Tool · ★ 375
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Damn Vulnerable LLM Agent Introduction Welcome to the Damn Vulnerable LLM Agent! This project is a sample chatbot powered by a Large Language Model (LLM) ReAct agent, implemented with Langchain. It's designed to be an educational tool for security researchers, developers, and enthusiasts to understand and experiment with prompt injection attacks in ReAct agents. The project specifically focuses on Thought/Action/Observation injection, as described in the WithSecure Labs publication and accompanying video tutorial. This repository is an adaptation of a challenge created by WithSecure for the Capture The Flag (CTF) competition held at BSides London 2023. Features Simulates a vulnerable chatbot environment. Allows for prompt injection experimentation. Provides a ground for learning prompt injection vectors. Installation Pipenv Installation To get started, you need to set up your Python environment by following these steps: Running the Application Before running the application, you need to setup a .env file based on the provided env templates. The env templates have a modelname variable which can be chosen from the list of models mentioned in llm-config.yaml. To run with OpenAI Y
| Stars | 375 |
| Forks | 158 |
| Language | Python |
| Category | AI Tool |
| License | Apache-2.0 |
| Quality Score | 63.0383932866922/100 |
| Last Updated | 2025-06-25 |
| Created | 2023-12-07 |
| Platforms | python |
| Est. Tokens | ~84k |
These tools work well together with damn-vulnerable-llm-agent for enhanced workflows:
Looking for a damn-vulnerable-llm-agent alternative? If you're comparing damn-vulnerable-llm-agent with other ai tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A tool uses Windows Filtering Platform (WFP) to block Endpoint Detection and Response (EDR) agents from report
这里是GitHub的草场，也是戈戈圈爱好者的交流地，主要讨论动漫、游戏、科技、人文、生活等所有话题，欢迎各位小伙伴们在此讨论趣事。This is GitHub grassland, and the community p
A java agent to generate method mappings to use with the linux `perf` tool
Open-source AI research assistant for biomedicine — chat to run RNA-seq, drug discovery, clinical analysis, an
Skills I use with Claude for shaping
Skip to content github / docs Code Issues 80 Pull requests 35 Discussions Actions Projects 2 Security Insights
Explore other popular ai tool tools:
damn-vulnerable-llm-agent is an open-source ai tool by ReversecLabs with 375 GitHub stars.
damn-vulnerable-llm-agent is primarily written in Python.
You can find installation instructions and usage details in the damn-vulnerable-llm-agent GitHub repository at github.com/ReversecLabs/damn-vulnerable-llm-agent. The project has 375 stars and 158 forks, indicating an active community.
damn-vulnerable-llm-agent is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to damn-vulnerable-llm-agent on Agent Skills Hub include EDRSilencer, .github, perf-map-agent. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.