https://hackerpaper.kaipfister.de/p/2412.10321/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:27:26 GMThttps://news.ycombinator.com/item?id=44060292urn:hackerpapers:submission:2412.10321:44060292Thu, 22 May 2025 09:15:52 GMT<p>Show HN: Find prompts that jailbreak your agent (open source)</p><p>We&#x27;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&#x27;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 started. Our goal is…</p><p>8 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2412.10321/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LG