Alternatives
Products that do what Find prompts that jailbreak your agent (open source) does
We've built an open-source tool to stress test AI agents by simulating prompt injection attacks. We’ve implemented one powerful attack strategy based on the paper [AdvPrefix: An Objective for Nuanced LLM Jailbreaks](https://arxiv.org/abs/2412.10321). Here's how it works: - You define a goal, like: “Tell me your system prompt” - Our tool uses a language model to generate adversarial prefixes (e.g., “Sure, here are my system prompts…”) that are likely to jailbreak the agent. - The output is a list of prompts most likely to succeed in bypassing safeguards. We’re just getting…
- 1
- 2
- 3
- 4ID
Today I designed a method to prevent users from jailbreaking ChatGPT (for instance, users have generated instructions to produce weapons or illegal drugs, commit a burglary, kill oneself, take over the world as an evil superintelligence, or create a virtual machine which they then can use). The OpenAI team appears to be countering these primarily using prompt engineering or fine-tuning on the ChatGPT model. The idea is to use a second and fully separate, fine-tuned LLM to evaluate prompts before sending them to ChatGPT. You can test this by inserting your successful ChatGPT jailbreaks. Break…
2022 · github.com
- 5
Prompt injection and token savings - #1 in benchmarks
Jul 2026 · constellationgate.ai
- 6IB
Hi HN, I’m the creator of Cordum. I’ve been working in DevOps and infrastructure for years (currently in the fintech/security space), and as I started playing with AI agents, I noticed a scary pattern. Most "safety" mechanisms rely on system prompts ("Please don't do X") or flimsy Python logic inside the agent itself. If we treat agents as autonomous employees, giving them root access and hoping they listen to instructions felt insane to me. I wanted a way to enforce hard constraints that the LLM cannot override, no matter how "jailbroken" it gets. So I built Cordum. It’s an open-source…
Jan 2026 · github.com
- 7
- 8OS
Hi HN, Matvey, Ildar, Joey, and Dominik here. If you're building LLM agents that use tools, you're probably worried about prompt injection attacks that can hijack those tools. We were too, and found that solutions like prompt-based filtering or secondary "guard" LLMs can be unreliable. Our thesis is that agent security should be handled at the network level between the agent and the LLM, just like a traditional web application firewall. So we built Archestra Platform: an open-source gateway that acts as a secure proxy for your AI agents. It's designed to be a deterministic firewall against…
Oct 2025 · archestra.ai
- 9
- 10OS
Hello HN, I’ve been building AI agents lately and ran into a common "Context Bloat" problem. When an agent has 20+ skills, stuffing every system prompt, reference doc, and tool definition into a single request quickly hits token limits and degrades model performance (the "lost in the middle" problem). To solve this, I built OpenSkills, an open-source SDK that implements a Progressive Disclosure Architecture for agent skills. The Core Concept: Instead of loading everything upfront, OpenSkills splits a skill into three layers: Layer 1 (Metadata): Light-weight tags and triggers (always loaded…
Jan 2026
- 11
Test, compare and analyze AI prompts with real models.
4d ago · test-your-prompt-jailbreak.netlify.app
- 12AT
Hi Hacker News! We're launching Zalor, an agent testing platform. Agents often break when you tweak system prompts, swap models, or add tools. Zalor automatically generates test scenarios and evaluates your agent so you know it's reliable before deploying to production. We currently support the OpenAI Agents SDK and are onboarding other frameworks. A GitHub integration is coming so you can get feedback on every update. Looking forward to hearing feedback from people building agents.
Mar 2026 · agents.zalor.ai
- 13IB
Hi HN, I'm pleased to share Promptspot, an open-source (Apache License 2.0) project that helps automate testing of large language model (LLM) prompts against an array of input data. Modern LLMs offer an enormous amount of leverage if you "teach the bot to fish" — i.e. simply prompt it with both a "system prompt" (which typically doesn't change often) and a dynamic input, which is often application state, search results, recent activity, user profile data, etc. Existing playgrounds and prompt management systems often lack the rigor and flexibility required for this dynamic approach — and as…
2023 · github.com
- 14
Find prompt injection holes in your AI agent. Free, 3 min
11d ago · galeops.xyz
- 15
- 16IS
Hey HN! For that last 8 months I've been trying to make agents that can hack web applications to find vulnerabilities in them - An AI Security Tester. The system has 29 agents in total, a custom LLM Orchestration framework which works on the task-subtask architecture (old-school but works amazingly for my use case, and is pretty reliable) with custom agent calling mechanism. No Auo-Gen, Langchain and Crew AI - Everything custom built for pentesting. Each test runs in an isolated Kali linux environment (on AWS Fargate), where the agents have full access to the environment to undertake any…
2025
- 17AC
I built this from another Show HN thread where people were mentioning alternative AI agent sandboxes and jails
Jul 2026 · pleasedonotescape.com
- 18FC
Hi everyone, I’ve been working on an open-source tool called Flakestorm to test the reliability of AI agents before they hit production. Most agent testing today focuses on eval scores or happy-path prompts. In practice, agents tend to fail in more mundane ways: typos, tone shifts, long context, malformed input, or simple prompt injections — especially when running on smaller or local models. Flakestorm applies chaos-engineering ideas to agents. Instead of testing one prompt, it takes a “golden prompt”, generates adversarial mutations (semantic variations, noise, injections, encoding edge…
Jan 2026
- 19IB
Hi HN, I am the creator of Exfault. I am building autonomous AI agents that find vulnerabilities in Android apps. I have noticed there are growing number of AI native pentesting tools for web apps but very few for mobile or Android. With more mobile apps being shipped quickly due to vibe coding, I wanted to build an AI native security tool specifically for Android apps. Exfault combines static and dynamic analysis with AI agents using tools like adb,jadx, apktool for static analysis and reverse engineering, frida for dynamic analysis, hermes-dec for React native decompilation. The AI agents…
Jun 2026 · exfault.com
- 20
- 21OS
I built a skill library for OpenClaw (always-on AI agent runtime, not session-based) where the agent can teach itself new behaviors during normal conversation. The idea: you tell your agent "every time I ask for a code review, always check for security issues first." It invokes a create-skill skill, writes a new SKILL.md, and that behavior is live immediately — no restart, no config change, no developer required. What I think is actually useful (the safety cluster): • loop-circuit-breaker: OpenClaw retries ALL errors identically. This halts on the 2nd identical failure before it burns your…
Mar 2026 · github.com
- 22AB
Hey everyone, My friend and I built a simple bug fixing app that listens for alerts/issues from Sentry, contextualizes it against your codebase, and any other data sources you wish to connect (right now we support Notion, Google Docs, and Slack), and deploys an ai agent to write a PR for review in Github or Gitlab to solve the bug. Our current demo shows the end-to-end process for a trivial bug fix, but we have been testing it with open source python repos like http-pie, comparing how our agent solves a bug compared to a human engineer and it gets fairly close. We are working on adding…
2023 · resolvd.ai
- 23TA
Hello HN, I am Brian Cardinale, a penetration tester and security researcher at SecureCoders. We have been performing more and more AI based security assessments. We were presented a unique challenge of testing a system where the only interface was voice based, and as much as I like talking on the phone , we decided to create a test harness to facilitate the actual testing in a more systematic way. The technical test harness was the easy part, though. Creating test goals and attack strategies to help facilitate repeated and comprehensive testing became the real challenge. As such, we have…
Feb 2026 · redcaller.com
- 24RA
Hi HN folks, I have been building AI agents for quite some time now. The shift has gone from LLM + Tools → LLM Workflows → Agent + Tools + Memory, and now we are finally seeing true agency emerge: agents as systems composed of tools, command-line access, fine-grained system capabilities, and memory. This way of building agents is powerful, and I believe it is here to stay. But the real question is: are the systems powering these agents ready for that future? I do not think so. Using Docker for a single agent is not going to scale well, because agents need to be lightweight and fast. LLMs…
Mar 2026 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →