Vulnerability Detection LLM LLM Tools

Tools and frameworks for detecting software vulnerabilities using LLMs, including source code analysis, binary analysis, and vulnerability classification. Does NOT include LLM application security, attack vectors against LLMs themselves, or general code quality analysis.

There are 38 vulnerability detection llm tools tracked. 1 score above 50 (established tier). The highest-rated is OWASP/www-project-top-10-for-large-language-model-applications at 54/100 with 1,145 stars.

Get all 38 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=llm-tools&subcategory=vulnerability-detection-llm&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Tool	Score	Tier	Stars	Language
1	OWASP/www-project-top-10-for-large-language-model-applications OWASP Top 10 for Large Language Model Apps (Part of the GenAI Security Project)	54	Established	1,145	Python
2	esbmc/esbmc-ai Automated Code Repair suite powered by ESBMC and LLMs.	43	Emerging	39	Python
3	cla7aye15I4nd/PatchAgent [USENIX Security 25] PatchAgent is a LLM-based practical program repair...	42	Emerging	120	Python
4	iSEngLab/AwesomeLLM4APR [TOSEM 2026]A Systematic Literature Review on Large Language Models for...	37	Emerging	232	—
5	waroad/losver Source Code for LOSVER: Line-Level Modifiability Signal-Guided Vulnerability...	33	Emerging	2	Python
6	YerbaPage/MGDebugger Multi-Granularity LLM Debugger [ICSE2026]	32	Emerging	96	Python
7	Mohannadcse/AlloySpecRepair An Empirical Evaluation of Pre-trained Large Language Models for Repairing...	31	Emerging	2	Alloy
8	youpengl/OpenVul OpenVul: An Open-Source Post-Training Framework for LLM-Based Vulnerability Detection	30	Emerging	29	Python
9	thanhlecongg/Invalidator Invalidator: Automated Patch Correctness Assessment via Semantic and...	29	Experimental	6	Python
10	GURPREETKAURJETHRA/LLM-SECURITY Securing LLM's Against Top 10 OWASP Large Language Model Vulnerabilities 2024	29	Experimental	22	—
11	lt-asset/resym For our CCS24 paper 🏆 "ReSym: Harnessing LLMs to Recover Variable and Data...	29	Experimental	131	Makefile
12	lambdasec/autogrep Autogrep automates Semgrep rule generation and filtering by using LLMs to...	28	Experimental	73	Python
13	jiangnanboy/llm_security 利用分类法和敏感词检测法对生成式大模型的输入和输出内容进行安全检测，尽早识别风险内容。The input and output contents of...	28	Experimental	28	Java
14	CUHK-Shenzhen-SE/D4C [ICSE'25] Aligning the Objective of LLM-based Program Repair	26	Experimental	23	Python
15	lin-tan/llm-vul For our ISSTA23 paper "How Effective are Neural Networks for Fixing Security...	26	Experimental	41	Java
16	adam-sse/geneseer A search-based automated program-repair tool for Java with LLM integration.	25	Experimental	3	Java
17	lambdasec/autofix Static Analysis meets Large Language Models	24	Experimental	53	Python
18	VulDet/PailGen An LLM-based model for vulnerability patch generation in C/C++ source code	24	Experimental	1	Python
19	jaimemorales52/llm-ioc-detection Spring Boot backend for evaluating Large Language Models on the detection of...	24	Experimental	12	Java
20	nghiempt/llm-analysis-privacy-policy Unveiling Discrepancies in Android App Data Safety Declarations and Privacy...	24	Experimental	3	Jupyter Notebook
21	GhabiX/SRepair ✅SRepair: Powerful LLM-based Program Repairer with $0.029/Fixed Bug	23	Experimental	74	Python
22	pdparchitect/llm-hacking-database This repository contains various attack against Large Language Models.	22	Experimental	132	—
23	garghub/VulnerabilityCouplingMutants On the Coupling between Vulnerabilities and LLM-generated Mutants: A Study...	22	Experimental	7	Java
24	KDEGroup/LLMVulnerabilityDetection Resources for our ICSE'24 poster: Prompt-Enhanced Software Vulnerability...	20	Experimental	25	—
25	soarsmu/midas MiDas: Multi-granularity Detector for Vulnerability Fixes (IEEE TSE)	17	Experimental	15	Python
26	AdityaBhatt3010/OWASP-Top-10-for-LLM-Apps-2025-Survival-Guide-for-Builders-Blue-Teams A survival playbook for engineers and blue teams - prompts, vectors, agents,...	16	Experimental	11	—
27	dtcxzyw/llvm-apr-benchmark A Large-Scale Automated Program Repair Benchmark of Real-World LLVM Middle-End Bugs	15	Experimental	22	Python
28	iSEngLab/LLM4VulFix [2023 TDSC] Pre-trained Model-based Automated Software Vulnerability Repair:...	15	Experimental	25	Python
29	kookmin-sw/capstone-2025-14 Automated Binary Vulnerability Analysis Using LLMs	14	Experimental	—	JavaScript
30	lhmtriet/LLM4Vul Reproduction package of the paper "Software Vulnerability Prediction in Low...	13	Experimental	6	Jupyter Notebook
31	Tomsawyerhu/GPT-O1-on-QuixBugs [APR 2025] Can GPT-O1 Kill All Bugs? An Evaluation of GPT-Family LLMs on QuixBugs	13	Experimental	5	—
32	Bobsimonoff/LLM-4-Applications-Commentary This repository contains thoughts, notes and observations on the OWASP Top...	13	Experimental	7	—
33	gfelber/llm_security_and_poisoning This project systematically evaluates the security risks in C code generated...	12	Experimental	1	C
34	BenderScript/owasp_llm_analysis Large Language Models Security Analsysis	12	Experimental	3	—
35	sysec-uic/AutoPatch-LLM ✨AutoPatch: LLM Based Low Level Memory Safety Bug Patching in C with...	12	Experimental	9	Python
36	SAILResearch/HAFix-History-Augmented-LLMs-for-Bug-Fixing HAFix is an approach that leverages historical heuristics associated with...	11	Experimental	—	Python
37	TalixAI/Elo SOTA AI Vulnerability Detection Model	11	Experimental	2	—
38	youpengl/MAVUL [TPS-ISA '25] MAVUL: Multi-Agent Vulnerability Detection via Contextual...	10	Experimental	3	Python

Comparisons in this category

www-project-top-10-for-large-language-model-applications and LLM-SECURITY (54 vs 29)