35 matches found
skills
Mercado de Habilidades de Trail of Bits Un mercado de complementos de Claude Code de Trail of Bits que proporciona habilidades para mejorar el análisis de seguridad asistido por IA, las pruebas y los flujos de trabajo de desarrollo. Codex puede cargar este mercado a través de su compatibilidad co...
c-sentinel
C-Sentinel UNIX 系统的语义可观测性 一个用 C 编写的轻量级、可移植的系统探测器，捕获“系统指纹”以实现 AI 辅助的非明显风险分析。功能包括 auditd 集成、可解释的风险评分，以及具有企业级多用户认证的实时 Web 仪表板。 在线演示 : sentinel.speytech.com 截图 安全仪表板 多主机概览 用户资料与安全设置 双因素认证...
gaia
Gaia - 攻击面发现与AI辅助分类 Gaia 是一个以 CLI 为主的攻击面分析工具，用于发现端点与参数、降低噪声，并利用静态启发式规则和可选的 AI 推理来突出安全相关风险。它编排了 Katana、gau、arjun、linkfinder 和 uro，将原始 URL 集合转化为规范化、风险感知的视图，适用于漏洞赏金、应用安全和安全工程工作流。 Gaia 不是一个自动化的漏洞扫描器。它映射攻击面、应用确定性启发式规则，并可以借助 LLM 生成测试提示。所发现的结果是指导性信息，而非确认的漏洞。需要手动验证。AI 输出仅作为建议而非权威结论，用于帮助决定关注重点和测试方法。 Gaia...
radmin-vpn-linux
适用于 Linux 的 Radmin VPN 通过 Wine 在 Linux 上运行 Radmin VPN。加入 VPN 网络、查看对等节点、畅玩游戏——无需 Windows 虚拟机。 我构建这个项目并不是因为它比虚拟机更简单。我构建它是因为我认为它比虚拟机更简单。 AI 辅助代码。 由人类与 Claude（Anthropic）协作构建。驱动程序、钩子和桥接层是在 Ghidra 的帮助下，对 Radmin VPN 未文档化的驱动程序协议进行了大量 AI 辅助逆向工程后编写的。该项目可用，但不提供任何保证。 与 Famatech 无关联。Radmin VPN 是专有软件——请自行从...
exploitarium
https://discord.gg/WytKH65ZR अनुसंधान, सहायता, दस्तावेज़ीकरण और रुचि रखने वालों के लिए अधिक उपयोगी जानकारी के लिए शामिल हों। कथन यह रिपॉजिटरी प्रकाशित होने पर अधूरा था। AI उपयोग के संबंध में, मेरा फ़ज़िंग वर्कफ़्लो एक सख्त वर्कफ़्लो के साथ AI द्वारा स्वचालित किया गया था। मैंने सभी फ़ज़िंग के लिए...
Research-on-CVE-2025-9998
Investigación sobre CVE-2025-9998 vulnerabilidad en CVE 2025-9998 y solución para esa vulnerabilidad con ayuda de inteligencia artificial...
gstack
gstack "I don't think I've typed like a line of code probably since December, basically, which is an extremely large change." — Andrej Karpathy, No Priors podcast, March 2026 When I heard Karpathy say this, I wanted to find out how. How does one person ship like a team of twenty? Peter Steinberge...
analise-vulnerabilidades-zabbix-notebooklm
🛡️ SQLi-Schwachstellenanalyse in Zabbix mit NotebookLM Themenheft, entwickelt als Abgabe der DIO-Projekt-Challenge Unter Verwendung von NotebookLM als aktives KI-Tool zur Kuratierung, Synthese und Organisation von Wissen im Bereich Cybersicherheit 📋 Index Kontext und Ziele Quellenkuratierung...
badger-builder
badger-builder badger-builder è uno strumento assistito dall'IA per generare profili dinamici per Brute Ratel C4. Basta fornire a badger-builder un flavor per il profilo desiderato e chiederà a OpenAI una configurazione adatta. Configurazioni del profilo listener/payload generate dall'IA: URI C2...
exploitarium
Statement This repo was incomplete when published. In regar...
CVE-2026-64187
In the Linux kernel, the following vulnerability has been resolved: xfs: fail recovery on a committed log item with no regions If the first op of a transaction is a bare transaction header len == sizeofstruct xfstransheader, xlogrecoveraddtotrans adds an item but no region, leaving it on ritemq...
GO-2026-5263 Mattermost doesn't verify channel membership when processing AI-assisted message rewrites in github.com/mattermost/mattermost-server
Mattermost doesn't verify channel membership when processing AI-assisted message rewrites in github.com/mattermost/mattermost-server. NOTE: The source advisory for this report contains additional versions that could not be automatically mapped to standard Go module versions. If this is causing...
rspwner
RSPWNER RSPWNER is a Rust-based AI-assisted CTF pwn assistant...
CERT-In Recommends 12-Hour Patching for Internet-Facing Flaws Amid AI-Assisted Attacks
The Indian Computer Emergency Response Team CERT-In has issued new guidelines requiring organizations to patch critical security vulnerabilities in internet-exposed systems within 12 hours of being flagged where "feasible" to safeguard against potential threats stemming from threat actors' abuse ...
CVE-2026-5163
Mattermost versions 11.5.x = 11.5.1 fail to verify channel membership when processing AI-assisted message rewrites which allows an authenticated attacker to read the content of threads in private channels and direct messages they do not have access to via a crafted request to the post rewrite...
Governing AI-Assisted Security Operations: A Design Science Framework for Operational Decision Support
Engineering managers increasingly must decide how to introduce generative artificial intelligence AI, retrieval-augmented generation, and coding agents into high-risk operational functions without weakening accountability, privacy, cost discipline, or auditability. The central message of this stu...
PT-2026-28104
Name of the Vulnerable Software and Affected Versions LibreChat versions prior to 0.8.3-rc1 Description An Insecure Direct Object Reference IDOR exists in the 'PUT /api/keys' endpoint. Due to the use of the JavaScript object spread operator after setting the authenticated user's ID, an...
PT-2026-28102
What are the limits of AI-assisted vulnerability hunting? I obtained 23 CVEs in one month. BentoML 8.2k CVE-2026-27905 HIGH SillyTavern 24.6k CVE-2026-26286 HIGH Plane 28.2k CVE-2026-27705 MEDIUM NocoDB 46.4k CVE-2026-28399 MEDIUM Mautic 8.4k CVE-2026-3105 HIGH File Browser 27.9k CVE-2026-28492...
Turning threat reports into detection insights with AI
Security teams routinely need to transform unstructured threat knowledge, such as incident narratives, red team breach-path writeups, threat actor profiles, and public reports into concrete defensive action. The early stages of that work are often the slowest. These include extracting tactics,...
