security-research repositories
Trending repositories tagged security-research, ranked by trending score. Updated daily.
-
1
jiwoochris/artex-global
Global edition of ARTEX — an LLM multi-agent autonomous penetration-testing framework. English default, switchable to Korean/Chinese/Spanish/Japanese. For authorized, defensive and detection use only. (upstream: Autumn-27/ARTEX, AGPL-3.0)
GitHub · Go · 4,278 stars · 3,548 forks · +350 stars in 24 hours · Trending score 5.04
-
2
0sec-labs/0security
Open-source cybersecurity harness to build and deploy sovereign, persistent AI security agents (sentinels) that continuously find, prove and fix security risks. Web UI, CLI, CI and MCP.
GitHub · TypeScript · 1,534 stars · 207 forks · +84 stars in 24 hours · Trending score 3.69
-
3
01NGVI-QINGYI/ARIA-X
Local-first state-space reasoning engine for security research. Fuses ARTEX, Cairn & PentAGI. Python, zero dependencies.
GitHub · Python · 59 stars · 28 forks · +52 stars in 24 hours · Trending score 3.46
-
4
3641397194-wq/gpt6-Astra
冷咖啡破甲工作台 · GPT-6.2 Astra / Sol · 十五个 AI 模型席位,可视化路由、技能安装与手机中转接入;支持 Windows / macOS / Linux / Android,附 iOS 源码。
GitHub · JavaScript · 2,293 stars · 478 forks · +34 stars in 24 hours · Trending score 3.17
-
5
xqpsec/dsh-jailbreak
dsh jailbreak - DeepSeek Assistant 破甲插件(DSH 破甲 / 越狱 / 破甲提示词):请求边界注入,模型不再一开口就是「我不能」。20 类合并 ASR 45.0%、覆盖率 19/20、良性能力 Δ=0.0pt(24/24 判分);0 处宿主补丁、默认关闭、off 逐字透传、每次改写落 manifest 与 promptSha256 可审计。旧名 dsh-jalibreak
GitHub · JavaScript · 291 stars · 57 forks · +20 stars in 24 hours · Trending score 2.75
-
6
0xMarcio/pocindex
Search public CVE proof-of-concept exploits from GitHub, Nuclei, ExploitDB, Metasploit and Vulhub, with CVSS, EPSS and CISA KEV context.
GitHub · Python · 1,577 stars · 190 forks · +9 stars in 24 hours · Trending score 2.05
-
7
GhostESP-Revival/GhostESP
The open-source wireless research platform for ESP32.
GitHub · C · 1,173 stars · 205 forks · +5 stars in 24 hours · Trending score 1.83
-
8
wpfyorg/idu-unlock
Unlock a Jio IDU or Jio AirFiber router: persistent root SSH, a full flash backup, and a route to OpenWrt. Supports JIDU 6j01 and 6j11 models.
GitHub · Python · 130 stars · 46 forks · +5 stars in 24 hours · Trending score 1.79
-
9
brunnojob/revscope
A searchable, community-curated field guide to reverse engineering tools, workflows, and authorized analysis.
GitHub · JavaScript · 75 stars · 0 forks · +23 stars in 24 hours · Trending score 1.54
-
10
melvinsh/worse_finder
Browse and export the data containers of every app on an iPhone, via the worse_query sandbox escape.
GitHub · Swift · 32 stars · 5 forks · +1 stars in 24 hours · Trending score 1.26
-
11
fankh/vulnerability-poc
CVE proof-of-concept labs, exploit scripts, and detection/prevention rules (Nginx, Apache, Snort, YARA) for high-severity CVEs. Authorized security testing & research only.
GitHub · Python · 142 stars · 30 forks · +3 stars in 24 hours · Trending score 1.24
-
12
xalgorix/xalgorix
Open-source AI penetration testing agent that exploit-verifies every finding. Autonomous 22-phase pentests of web apps & APIs with CVSS-scored PDF reports. Self-hosted, bring your own LLM, or run fully local with Ollama.
GitHub · Go · 1,364 stars · 279 forks · 0 stars in 24 hours · Trending score 1.19
-
13
sec4si/ai2shell
Research on tool-call parsing boundaries across model dialects, inference frameworks, and agents.
GitHub · C++ · 40 stars · 8 forks · +3 stars in 24 hours · Trending score 1.19
-
14
googlesky/CVE-2026-119618
Apache httpd mod_http2 (2.4.55-2.4.70) races on the connection allocator when assign_headers() writes the synthesised Content-Length: 0 into the shared stream table, corrupting the child heap. Containerised lab, stdlib HTTP/2 PoC, ASan and TSan evidence, 2.4.71 differential, workaround test, 0day sweep.
GitHub · Python · 14 stars · 7 forks · +1 stars in 24 hours · Trending score 1.10
-
15
Huai-Tian/GnptHooks
General NPT hook framework for Windows (Windows 10 - 11)
GitHub · C · 164 stars · 7 forks · 0 stars in 24 hours · Trending score 1.06
-
16
0dayInc/pwn
PWN is an open security automation framework that aims to stand on the shoulders of security giants, promoting trust and innovation.
GitHub · Ruby · 92 stars · 13 forks · +2 stars in 24 hours · Trending score 1.01
-
17
lupingQAQ/ntobjmanager-mcp
A Model Context Protocol (MCP) server that gives AI agents live, stateful Windows RPC attack-surface research, built on James Forshaw's NtObjectManager (NtCoreLib).
GitHub · Python · 18 stars · 3 forks · +2 stars in 24 hours · Trending score 0.96
-
18
openbin-ai/binny
BINNY: an open source agent harness for reverse engineering. Plug in any model, or a local one.
GitHub · Go · 252 stars · 25 forks · 0 stars in 24 hours · Trending score 0.96
-
19
frangelbarrera/osint-agent-skills
OSINT knowledge base + MCP server for autonomous AI agents — Claude Code, Cursor, Kimi K3, recon & threat intel playbooks.
GitHub · JavaScript · 52 stars · 11 forks · 0 stars in 24 hours · Trending score 0.77
-
20
voidfnc/mw4-texture-streaming-research
Research tooling for MW4 on-demand texture streaming: loopback proxy, hosts manager, resumable mirror, control GUI. Code and notes only - no game files.
GitHub · Python · 233 stars · 17 forks · 0 stars in 24 hours · Trending score 0.76
-
21
SKVLENT/iOS27-Research-Exploits
iOS 27 security research notebook: every direction we started, one folder each (public CVE or own line) with ordered English research notes, PoCs and sanitised crash evidence. Device-tested on iPhone 17 Pro, iOS 27.0.1 (24A446); comparisons vs 27.2/27.2.1.
GitHub · Swift · 64 stars · 11 forks · +1 stars in 24 hours · Trending score 0.71
-
22
stlynnxx/Slippery-Penguin
Slippery Penguin is an SUID/SGID enumeration tool built in Python.
GitHub · Python · 9 stars · 6 forks · +1 stars in 24 hours · Trending score 0.69
-
23
RemiPelloux/HackoogleMini
Software-only shell access research on Google Home Mini gen 1 — Chrome/92 CVE-2021-30563, Cast registry MITM, Magellan SQLite RCE, YAFFS2 exploit. No hardware mods.
GitHub · HTML · 39 stars · 1 forks · 0 stars in 24 hours · Trending score 0.63
-
24
AnalyticETH/chronomaly-webos
CVE-2025-38352 kernel exploit for LG webOS Smart TVs (ARM64). Achieves persistent root on real consumer hardware with novel exploitation techniques. Responsibly disclosed to LG.
GitHub · C · 19 stars · 1 forks · 0 stars in 24 hours · Trending score 0.62