LlamaFirewall: An open source guardrail system for building secure AI agents · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2505.03574/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTLlamaFirewall: An open source guardrail system for building secure AI agents — mentioned by CuriouslyChttps://news.ycombinator.com/item?id=47036548urn:hackerpapers:mention:2505.03574:47036548Mon, 16 Feb 2026 15:51:32 GMT<p>These papers have example prompt injections datasets you can mine for examples. Then apply the techniques used in provider specific jailbreaks from Pliny to the template to increase the escape success rate. https://arxiv.org/abs/2506.05446 https://arxiv.org/abs/2505.03574 https://arxiv.org/abs/2501.15145</p><p><a href="https://hackerpaper.kaipfister.de/p/2505.03574/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CR