{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T15:44:37Z","timestamp":1787067877980,"version":"build-2736575974"},"reference-count":52,"publisher":"Association for Computing Machinery (ACM)","issue":"FSE","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Softw. Eng."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>Security vulnerabilities in software packages are a significant concern for developers and users alike. Patching these vulnerabilities in a timely manner is crucial to restoring the integrity and security of software systems. However, previous work has shown that vulnerability reports often lack proof-of-concept (PoC) exploits, which are essential for fixing the vulnerability, testing patches, and avoiding regressions. Creating a PoC exploit is challenging because vulnerability reports are informal and often incomplete, and because it requires a detailed understanding of how inputs passed to potentially vulnerable APIs may reach security-relevant sinks. In this paper, we present PoCGen, a novel approach to autonomously generate and validate PoC exploits for vulnerabilities in npm packages. The approach combines the complementary strengths of LLMs (e.g.,  \nunderstanding informal vulnerability reports), static analysis (e.g., identifying taint paths), and dynamic analysis (e.g., validating generated exploits). PoCGen successfully generates exploits for 71% of the vulnerabilities in the SecBench.js dataset. This success rate significantly outperforms a recent baseline (by 38 absolute percentage points), while imposing an average cost of only $0.02 per generated exploit. Moreover, PoCGen generates successful exploits for 60% of 126 recent real-world vulnerabilities, which helped augment five recent vulnerability reports in the GitHub Security Advisories database with PoCGen-generated PoC exploits.<\/jats:p>","DOI":"10.1145\/3808178","type":"journal-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:06:14Z","timestamp":1782839174000},"page":"3887-3908","source":"Crossref","is-referenced-by-count":1,"title":["PoCGen: Generating Proof-of-Concept Exploits for Vulnerabilities in Npm Packages"],"prefix":"10.1145","volume":"3","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0007-0799-2830","authenticated-orcid":false,"given":"Deniz","family":"Simsek","sequence":"first","affiliation":[{"name":"University of Stuttgart, Stuttgart, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0001-9763-8147","authenticated-orcid":false,"given":"Aryaz","family":"Eghbali","sequence":"additional","affiliation":[{"name":"CISPA Helmholtz Center for Information Security, Stuttgart, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0003-1623-498X","authenticated-orcid":false,"given":"Michael","family":"Pradel","sequence":"additional","affiliation":[{"name":"CISPA Helmholtz Center for Information Security, Stuttgart, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,30]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"n. d.]. CVE: Common Vulnerabilities and Exposures. https:\/\/2.zoppoz.workers.dev:443\/https\/www.cve.org\/about\/Metrics. Accessed: 2025-05-14."},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2402.13291"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2017.2785841"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE55347.2025"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","unstructured":"Islem Bouzenia and Michael Pradel. 2025. You Name It I Run It: An LLM Agent to Execute Tests of Arbitrary Projects. In ISSTA. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/3728922 10.1145\/3728922","DOI":"10.1145\/3728922"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2023.3286301"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2025.241636"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP57164.2023.00068"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2305.15336"},{"key":"e_1_2_1_12_1","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Ponde de Oliveira Pinto Jared Kaplan Harrison Edwards Yuri Burda Nicholas Joseph Greg Brockman Alex Ray Raul Puri Gretchen Krueger Michael Petrov Heidy Khlaaf Girish Sastry Pamela Mishkin Brooke Chan Scott Gray Nick Ryder Mikhail Pavlov Alethea Power Lukasz Kaiser Mohammad Bavarian Clemens Winter Philippe Tillet Felipe Petroski Such Dave Cummings Matthias Plappert Fotios Chantzis Elizabeth Barnes Ariel Herbert-Voss William Hebgen Guss Alex Nichol Alex Paino Nikolas Tezak Jie Tang Igor Babuschkin Suchir Balaji Shantanu Jain William Saunders Christopher Hesse Andrew N. Carr Jan Leike Joshua Achiam Vedant Misra Evan Morikawa Alec Radford Matthew Knight Miles Brundage Mira Murati Katie Mayer Peter Welinder Bob McGrew Dario Amodei Sam McCandlish Ilya Sutskever and Wojciech Zaremba. 2021. Evaluating Large Language Models Trained on Code. CoRR abs\/2107.03374 (2021). arXiv:2107.03374 https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2107.03374"},{"key":"e_1_2_1_13_1","first-page":"847","volume-title":"33rd USENIX Security Symposium (USENIX Security 24)","author":"Deng Gelei","year":"2024","unstructured":"Gelei Deng, Yi Liu, V\u00edctor Mayoral-Vilches, Peng Liu, Yuekang Li, Yuan Xu, Tianwei Zhang, Yang Liu, Martin Pinzger, and Stefan Rass. 2024. {PentestGPT}: Evaluating and Harnessing Large Language Models for Automated Penetration Testing. In 33rd USENIX Security Symposium (USENIX Security 24). 847-864."},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP40000.2020.00009"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524842.3528452"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","unstructured":"Yi Gao Xing Hu Zirui Chen and Xiaohu Yang. 2025. Vulnerability-Triggering Test Case Generation from Third-Party Libraries. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.48550\/arXiv.2409.16701 arXiv:2409.16701 [cs] 10.48550\/arXiv.2409.16701","DOI":"10.48550\/arXiv.2409.16701"},{"key":"e_1_2_1_17_1","volume-title":"Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018","author":"Harer Jacob","year":"2018","unstructured":"Jacob Harer, Onur Ozdemir, Tomo Lazovich, Christopher P. Reale, Rebecca L. Russell, Louis Y. Kim, and Sang Peter Chin. 2018. Learning to Repair Software Vulnerabilities with Generative Adversarial Networks. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, 3-8 December 2018, Montr\u00e9al, Canada. 7944-7954. https:\/\/2.zoppoz.workers.dev:443\/http\/papers.nips.cc\/paper\/8018-learning-to-repair-softwarevulnerabilities-with-generative-adversarial-networks"},{"key":"e_1_2_1_18_1","unstructured":"Allen D Householder Jeff Chrabaszcz Trent Novelly and David Warren. 2020. Historical Analysis of Exploit Availability Timelines. (2020)."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00125"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3613892"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP46215.2023.10179352"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3243734.3243804"},{"key":"e_1_2_1_23_1","first-page":"121","volume-title":"23rd International Symposium on Research in Attacks, Intrusions and Defenses (RAID 2020","author":"Koishybayev Igibek","year":"2020","unstructured":"Igibek Koishybayev and Alexandros Kapravelos. 2020. Mininode: Reducing the Attack Surface of Node.js Applications. In 23rd International Symposium on Research in Attacks, Intrusions and Defenses (RAID 2020). USENIX Association, San Sebastian, 121-134. https:\/\/2.zoppoz.workers.dev:443\/https\/www.usenix.org\/conference\/raid2020\/presentation\/koishybayev"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00085"},{"key":"e_1_2_1_25_1","volume-title":"UNIFUZZ: A Holistic and Pragmatic Metrics-Driven Platform for Evaluating Fuzzers. In USENIX Security.","author":"Li Yuwei","year":"2021","unstructured":"Yuwei Li, Shouling Ji, Yuan Chen, Sizhuang Liang, Wei-Han Lee, Yueyao Chen, Chenyang Lyu, Chunming Wu, Raheem Beyah, Peng Cheng, Kangjie Lu, and Ting Wang. 2021. UNIFUZZ: A Holistic and Pragmatic Metrics-Driven Platform for Evaluating Fuzzers. In USENIX Security."},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468597"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss"},{"key":"e_1_2_1_28_1","unstructured":"Ziyang Li Saikat Dutta and Mayur Naik. 2024. LLM-Assisted Static Analysis for Detecting Security Vulnerabilities. arXiv:2405.17238 [cs.CR]"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","unstructured":"Chengwei Liu Sen Chen Lingling Fan Bihuan Chen Yang Liu and Xin Peng. 2022. Demystifying the Vulnerability Propagation and Its Evolution via Dependency Trees in the NPM Ecosystem. In ICSE. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/3510003. 3510142 10.1145\/3510003.3510142","DOI":"10.1145\/3510003"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","unstructured":"Filipe Marques Mafalda Ferreira Andr\u00e9 Nascimento Miguel E Coimbra Nuno Santos Limin Jia and Jos\u00e9 Fragoso Santos. 2025. Automated Exploit Generation for Node.js Packages. In PLDI. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/3729304 10.1145\/3729304","DOI":"10.1145\/3729304"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","unstructured":"Yu Nong Yuzhe Ou Michael Pradel Feng Chan and Haipeng Cai. 2023. VulGen: Realistic Vulnerability Generation Via Pattern Mining and Deep Learning. In ICSE. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/ICSE48619.2023.00211 10.1109\/ICSE48619.2023.00211","DOI":"10.1109\/ICSE48619.2023.00211"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549128"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.562"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2023.3334955"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","unstructured":"Adriana Sejfia and Max Schaefer. 2022. Practical Automated Detection of Malicious npm Packages. In ICSE. https: \/\/doi.org\/10.1145\/3510003.3510104 10.1145\/3510003.3510104","DOI":"10.1145\/3510003.3510104"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE55347.2025.00239"},{"key":"e_1_2_1_37_1","volume-title":"Freezing the Web: A Study of ReDoS Vulnerabilities in JavaScriptbased Web Servers. In USENIX Security Symposium. 361-376","author":"Staicu Cristian-Alexandru","year":"2018","unstructured":"Cristian-Alexandru Staicu and Michael Pradel. 2018. Freezing the Web: A Study of ReDoS Vulnerabilities in JavaScriptbased Web Servers. In USENIX Security Symposium. 361-376."},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2018.23071"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3623345"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460120.3484535"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3650212.3680323"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","unstructured":"Jiacen Xu Jack W. Stokes Geoff McDonald Xuesong Bai David Marshall Siyue Wang Adith Swaminathan and Zhou Li. 2024. AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.48550\/arXiv.2403.01038 arXiv:2403.01038 [cs] 10.48550\/arXiv.2403.01038","DOI":"10.48550\/arXiv.2403.01038"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2210.08374"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1601"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510457.3513044"},{"key":"e_1_2_1_46_1","unstructured":"Michal Zalewski. 2013. American Fuzzy Lop (AFL). https:\/\/2.zoppoz.workers.dev:443\/https\/lcamtuf.coredump.cx\/afl\/. https:\/\/2.zoppoz.workers.dev:443\/https\/lcamtuf.coredump.cx\/afl\/"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","unstructured":"Yuntong Zhang Haifeng Ruan Zhiyu Fan and Abhik Roychoudhury. 2024. AutoCodeRover: Autonomous Program Improvement. In ISSTA. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/3650212.3680384 10.1145\/3650212.3680384","DOI":"10.1145\/3650212.3680384"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","unstructured":"Ying Zhang Wenjia Song Zhengjie Ji Danfeng Yao and Na Meng. 2023. How Well Does LLM Generate Security Tests? https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.48550\/arXiv.2310.00710 arXiv:2310.00710 [cs] 10.48550\/arXiv.2310.00710","DOI":"10.48550\/arXiv.2310.00710"},{"key":"e_1_2_1_49_1","unstructured":"Yuntong Zhang Jiawei Wang Dominic Berzin Martin Mirchev Dongge Liu Abhishek Arya Oliver Chang and Abhik Roychoudhury. 2024. Fixing Security Vulnerabilities with AI in OSS-Fuzz. arXiv:2411.03346 [cs.CR] https: \/\/arxiv.org\/abs\/2411.03346"},{"key":"e_1_2_1_50_1","volume-title":"Proceedings of the 31st USENIX Security Symposium.","author":"Zhang Zenong","year":"2022","unstructured":"Zenong Zhang, Zach Patterson, Michael Hicks, and Shiyi Wei. 2022. FixReverter: A Realistic Bug Injection Methodology for Benchmarking Fuzz Testing. In Proceedings of the 31st USENIX Security Symposium."},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP52600.2021.00020"},{"key":"e_1_2_1_52_1","first-page":"995","volume-title":"Small World with High Risks: A Study of Security Threats in the Npm Ecosystem. In 28th USENIX Security Symposium (USENIX Security 19)","author":"Zimmermann Markus","year":"2019","unstructured":"Markus Zimmermann, Cristian-Alexandru Staicu, Cam Tenny, and Michael Pradel. 2019. Small World with High Risks: A Study of Security Threats in the Npm Ecosystem. In 28th USENIX Security Symposium (USENIX Security 19). 995-1010."}],"container-title":["Proceedings of the ACM on Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/pdf\/10.1145\/3808178","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:52:40Z","timestamp":1782841960000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/10.1145\/3808178"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":52,"journal-issue":{"issue":"FSE","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1145\/3808178"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/3808178","relation":{},"ISSN":["2994-970X"],"issn-type":[{"value":"2994-970X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,30]]}}}