PoCGen: Generating Proof-of-Concept Exploits for Vulnerabilities in Npm Packages
Deniz Simsek, Aryaz Eghbali, Michael Pradel
Abstract
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., understanding 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.
CCS Concepts: • Security and privacy → Software and application security.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers3
- V2E: Validating Smart Contract Vulnerabilities through Profit-Driven Exploit Generation and ExecutionJingwen Zhang, Yuhong Nan, Kaiwen Ning, Mingxi Ye et al.FSE 2026
- PAGENT: Program Analysis Guided LLM Agent for Proof-of-Concept GenerationAchintya Desai, Md Shafiuzzaman, Wenbo Guo, Tevfik BultanISSTA 2026
- Exploring Motif-based Heterogeneous Graph Learning for ReDoS DetectionHong Huang, Chengyu Yao, Rongchen Li, Weihao Su et al.ICML 2026
Builds on28
- SWE-agent: Agent-Computer Interfaces Enable Automated Software EngineeringJohn Yang, Carlos E. Jimenez, Alexander Wettig, Kilian Lieret et al.NeurIPS 2024 · 2,059 citations
- A Security Analysis of HoneywordsDing Wang, Haibo Cheng, Ping Wang, Jeff Yan et al.NDSS 2018 · 1,102 citations
- Coverage-based Greybox Fuzzing as Markov ChainMarcel Böhme, Van-Thuan Pham, Abhik RoychoudhuryCCS 2016 · 1,026 citations
- Evaluating Fuzz TestingGeorge Klees, Andrew Ruef, Benji Cooper, Shiyi Wei et al.CCS 2018 · 753 citations
- Vulnerability detection with fine-grained interpretationsYi Li, Shaohua Wang, Tien N. NguyenFSE 2021 · 283 citations
Related papers
- PoCE: Automated Proof-of-Concept Synthesis using Large Language Models for Robust ValidationTanusree Das Tithy, Lamia Hasan Rodoshi, Ayman Rafid Azahar, Amlan Abhidarshi et al.ISSTA 2026
- Automated Exploit Generation for Node.js PackagesFilipe Marques, Mafalda Ferreira, André Nascimento, Miguel E. Coimbra et al.PLDI 2025 · 5 citations
- Learning from the Past: Real-World Exploit Migration for Smart Contract PoC GenerationKairan Sun, Zhengzi Xu, Kaixuan Li, Lyuye Zhang et al.ASE 2025 · 3 citations
- SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security TasksHwiwon Lee, Ziqi Zhang, Hanxiao Lu, Lingming ZhangNeurIPS 2025 · 86 citations
- SemFuzz: Semantics-based Automatic Generation of Proof-of-Concept ExploitsWei You, Peiyuan Zong, Kai Chen, XiaoFeng Wang et al.CCS 2017 · 148 citations
