{"slug": "snyk-vulnbench-javascript-1-0-can-llms-find-the-same-bugs-twice", "title": "Snyk VulnBench JavaScript 1.0: Can LLMs Find the Same Bugs Twice?", "summary": "A new benchmark, Snyk VulnBench JavaScript 1.0, reveals that large language models (LLMs) produce inconsistent vulnerability findings across repeated scans of the same JavaScript code, with 80 of 161 unique unmatched findings appearing in only one of five identical runs. In contrast, reference-matched findings were stable, and Snyk Code's deterministic SAST tool outperformed LLMs in systematically enumerating data-flow sinks. The results suggest combining agentic LLM review with deterministic SAST rather than using either alone.", "body_md": "# Computer Science > Cryptography and Security\n\n[Submitted on 14 Jun 2026]\n\n# Title:Snyk VulnBench JS 1.0: Can LLMs Find the Same Bugs Twice?\n\n[View PDF](/pdf/2606.15762)\n\n[HTML (experimental)](https://arxiv.org/html/2606.15762v1)\n\nAbstract:We ran 300 repeated vulnerability-finding scans to measure how repeatable agentic large language model (LLM) security review is on the same JavaScript code, prompt, and benchmark harness. The headline result is that LLM security findings were unevenly repeatable: reference-matched findings were stable, but extra model reports varied heavily from run to run. Across 250 model runs, 80 of 161 unique unmatched findings appeared in only one of five identical repetitions, while only 22 appeared in all five. By contrast, when Claude matched a Snyk Code reference finding, the behavior was much more stable: 134 of 158 unique reference-matched findings appeared in all five repetitions. The benchmark also shows complementarity. Models consistently found familiar, high-signal exploit shapes, and in one case surfaced a likely Snyk Code product gap. Snyk Code static application security testing (SAST) was deterministic and better at systematically enumerating repeated data-flow sinks. The results support combining agentic LLM review with deterministic SAST rather than treating either technique as a replacement for the other.\n\n### Current browse context:\n\ncs.CR\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/snyk-vulnbench-javascript-1-0-can-llms-find-the-same-bugs-twice", "canonical_source": "https://arxiv.org/abs/2606.15762", "published_at": "2026-06-16 16:32:45+00:00", "updated_at": "2026-06-16 16:53:23.873917+00:00", "lang": "en", "topics": ["large-language-models", "ai-safety", "ai-research", "ai-tools", "developer-tools"], "entities": ["Snyk", "Claude", "Snyk Code", "Snyk VulnBench JavaScript 1.0"], "alternates": {"html": "https://wpnews.pro/news/snyk-vulnbench-javascript-1-0-can-llms-find-the-same-bugs-twice", "markdown": "https://wpnews.pro/news/snyk-vulnbench-javascript-1-0-can-llms-find-the-same-bugs-twice.md", "text": "https://wpnews.pro/news/snyk-vulnbench-javascript-1-0-can-llms-find-the-same-bugs-twice.txt", "jsonld": "https://wpnews.pro/news/snyk-vulnbench-javascript-1-0-can-llms-find-the-same-bugs-twice.jsonld"}}