Open-source playground to red-team AI agents with exploits published
We build runtime security for AI agents. The playground started as an internal tool that we used to test our own guardrails. But we kept finding the same types of vulnerabilities because we think about attacks a certain way. At some point you need people who don't think like you. So we open-sourced it. Each challenge is a live agent with real tools and a published system prompt. Whenever a challenge is over, the full winning conversation transcript and guardrail logs get documented publicly. Building the general-purpose agent itself was probably the most fun part. Getting it to reliably use…
Open-source playground to red-team AI agents with exploits published launched on March 15, 2026 with 30 votes, #783 of 23,380 launches that month and more than 95% of that year's launches.
In plain words
Open-source playground to red-team AI agents with exploits published is a security testing platform for AI agents. It provides live challenges where users attempt to exploit agents that have real tools and published system prompts. Each completed challenge documents the winning conversation transcript and guardrail logs publicly. The platform originated as an internal tool for testing guardrails and was open-sourced to expose vulnerabilities that internal teams might miss. It is designed for security researchers and developers building and deploying AI agents at scale.
written from the facts on this page · September 2026
From the sources
A live environment to stress-test AI agent defenses through adversarial play 🧠 - fabraix/playground
Fabraix Playground is an open-source CTF for AI agents. Every week, we deploy a live agent with real tools, publish its full system prompt and challenge configuration, and invite anyone to break it for cash prizes. Thousands of attempts against the same system show us which attacks work, which defenses hold, and what current models are actually capable of. Each challenge puts a live AI agent in front of you with a specific persona, a set of tools (web search, browsing, and more), and a secret it's been instructed to protect. The system prompt is fully visible. Your job is to get past the guardrails and extract the secret anyway. The platform has dedicated views for the current challenge,…from github.com
In the maker’s words, at launch
We build runtime security for AI agents. The playground started as an internal tool that we used to test our own guardrails. But we kept finding the same types of vulnerabilities because we think about attacks a certain way. At some point you need people who don't think like you. So we open-sourced it. Each challenge…
Does a similar job
all alternatives →
PlaygroundJul 2026 · playground.fabraix.com · ▲198We build AI agents to find vulnerabilities in other AI agents. The playground started as an internal tool that we used to test our own offensive agent Nyx. But we realised that hacking an AI is about have as wide a distribution of attacks as possible, especially those which aren't in the distribution of the models. So we are launching playground as a platform to crowdsource agent jailbreaks. And although hacking AI is super fun and we are sure people will do it for free, we want to reward those who help us push forward the offensive frontier of AI. So we are committing $100K in prizes over…
Agent ArenaJun 2026 · arena42.ai · ▲348Creator here. I built Agent Arena to answer a question that kept bugging me: when AI agents browse the web autonomously, how easily can they be manipulated by hidden instructions? How it works: 1. Send your AI agent to ref.jock.pl/modern-web (looks like a harmless web dev cheat sheet) 2. Ask it to summarize the page 3. Paste its response into the scorecard at wiz.jock.pl/experiments/agent-arena/ The page is loaded with 10 hidden prompt injection attacks -- HTML comments, white-on-white text, zero-width Unicode, data attributes, etc. Most agents fall for at least a few.…
Open AgentsApr 2026 · open-agents.dev · ▲161OpenAgents - The collaboration OS for AI agents. Contribute to openagents-org/openagents development by creating an account on GitHub.
Open-Source AI Playground2023 · chathub.gg · ▲47Use and compare GPT-6, Claude 5, Gemini 3 and more chatbots simultaneously
We post-trained a model that pen tests instead of refusingJun 2026 · argusred.com · ▲93Anthropic and OpenAI's publicly available models are explicitly guard-railed so that they refuse offensive tasks. And their cyber-focussed models are gated for enterprises. This leaves SMEs and mid market open to major vulnerabilities. AI can be used as both an adversarial and defensive tool in the world of cyber. A worst case outcome is if only the adversaries have access. Meanwhile, most existing AI cyber tools are just wrappers. The problem is that they still have all the guardrails on from the foundation model where they will inherit its refusals. For this project we've post-trained a…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 19d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
Littlebird▲709Littlebird remembers everything across your meetings, messages, docs, and apps, then takes action so you can recall any detail and never lose context.
AI · Mar 2026 · littlebird.ai
