26 matches found
AI-Infra-Guard
📖 ドキュメント | 🌐 🇬🇧 English · 🇨🇳 中文 · 🇯🇵 日本語 · 🇪🇸 Español · 🇩🇪 Deutsch · 🇫🇷 Français · 🇰🇷 한국어 · 🇧🇷 Português · 🇷🇺 Русский...
OWASP-Top-10-AI-Infrastructure-Security-Risks
数据中心与AI基础设施安全风险Top 10 FORGE - 加固模型之下的金属层。 🌐 网站： https://forge-framework.io 执行摘要 AI数据中心的建设速度远超其安全防护速度。 数据中心、GPU云和专用计算环境的快速扩张，在硬件、网络、存储、编排、身份、管理平面和物理运维等方面引入了安全风险。其中许多风险与传统数据中心或云安全问题相似，但现代数据中心和AI基础设施改变了其严重程度：原本为可信运营商设计的系统，如今正在支撑来自无关客户的高价值、多租户工作负载。 数据中心与AI基础设施安全风险Top 10...
LifeOS 7.28.3
LifeOS is a Life Operating System. It knows your goals, the people who matter to you, and where you are right now, and it works to move you toward where you want to be. The engine underneath is a verifiable loop: turn any request into testable criteria, then climb until they pass. This is the fir...
A Sneaky Hacking Tool Targeting AI Infrastructure Is Lurking in Victims’ Blind Spots
A new type of malware can worm deep into AI coding systems to steal data and logins—and can flip a “death switch” to destroy files and keep out real users...
New ENCFORGE Ransomware Targets AI Model Files in Langflow RCE Attack
Researchers at Sysdig have linked a second attack on the same Langflow server to JADEPUFFER, the AI-agent-driven operator it first documented earlier this month. The same operator has now been spotted deploying ENCFORGE , a new compiled Go ransomware designed to encrypt model weights, vector...
From Langflow to Monero: Inside CVE-2026-33017 Cryptominer
We tracked a cryptocurrency-mining campaign exploiting CVE-2026-33017, which revealed how threat actors are now scanning exposed AI application infrastructure for their next foothold...
Hunting Vulnerability Variants in AI Infra: Measurement and Reference-Driven Detection
AI infra has become a shared execution layer for model training, deployment, and agent orchestration. Because many projects reimplement similar model-centric workflows, a vulnerability disclosed in one repository can recur as a variant in another repository with a related design. Yet the prevalen...
We Scanned 1 Million Exposed AI Services. Here's How Bad the Security Actually Is
While the software industry has made genuine strides over the past few decades to deliver products securely, the furious pace of AI adoption is putting that progress at risk. Businesses are moving fast to self-host LLM infrastructure, drawn by the promise of AI as a force multiplier and the...
security-advisories
Security Advisories Public write-ups and PoCs for CVEs I've d...
CVE-2026-6141
A vulnerability was determined in danielmiessler PersonalAIInfrastructure up to 2.3.0. Affected is an unknown function of the file Skills/Parser/Tools/parseurl.ts. Executing a manipulation can lead to os command injection. The attack may be launched remotely. The exploit has been publicly disclos...
CVE-2026-6141
A vulnerability was determined in danielmiessler PersonalAIInfrastructure up to 2.3.0. Affected is an unknown function of the file Skills/Parser/Tools/parseurl.ts. Executing a manipulation can lead to os command injection. The attack may be launched remotely. The exploit has been publicly disclos...
CVE-2026-6141 danielmiessler Personal_AI_Infrastructure parse_url.ts os command injection
A vulnerability was determined in danielmiessler PersonalAIInfrastructure up to 2.3.0. Affected is an unknown function of the file Skills/Parser/Tools/parseurl.ts. Executing a manipulation can lead to os command injection. The attack may be launched remotely. The exploit has been publicly disclos...
CVE-2026-6141 danielmiessler Personal_AI_Infrastructure parse_url.ts os command injection
A vulnerability was determined in danielmiessler PersonalAIInfrastructure up to 2.3.0. Affected is an unknown function of the file Skills/Parser/Tools/parseurl.ts. Executing a manipulation can lead to os command injection. The attack may be launched remotely. The exploit has been publicly disclos...
CVE-2026-6141
A vulnerability was determined in danielmiessler PersonalAIInfrastructure up to 2.3.0. Affected is an unknown function of the file Skills/Parser/Tools/parseurl.ts. Executing a manipulation can lead to os command injection. The attack may be launched remotely. The exploit has been publicly disclos...
CVE-2026-6141 danielmiessler Personal_AI_Infrastructure parse_url.ts os command injection
A vulnerability was determined in danielmiessler PersonalAIInfrastructure up to 2.3.0. Affected is an unknown function of the file Skills/Parser/Tools/parseurl.ts. Executing a manipulation can lead to os command injection. The attack may be launched remotely. The exploit has been publicly disclos...
CVE-2026-6141
The CVE-2026-6141 entry affects danielmiessler Personal_AI_Infrastructure up to version 2.3.0, targeting an unknown function in Skills/Parser/Tools/parse_url.ts. The vulnerability allows remote OS command injection via manipulation of that function. The exploit has been publicly disclosed, and a ...
PT-2026-32198
A vulnerability was determined in danielmiessler Personal AI Infrastructure up to 2.3.0. Affected is an unknown function of the file Skills/Parser/Tools/parse url.ts. Executing a manipulation can lead to os command injection. The attack may be launched remotely. The exploit has been publicly...
Personal AI Infrastructure 操作系统命令注入漏洞
Personal AI Infrastructure is a personal AI infrastructure building tool developed by Daniel Miessler as a personal project. Versions of Personal AI Infrastructure prior to 2.3.0 contained a vulnerability related to operating system command injection. This vulnerability stemmed from improper...
AI is Everywhere, But CISOs are Still Securing It with Yesterday's Skills and Tools, Study Finds
A majority of security leaders are struggling to defend AI systems with tools and skills that are not fit for the challenge, according to the AI and Adversarial Testing Benchmark Report 2026 from Pentera. The report, based on a survey of 300 US CISOs and senior security leaders, examines how...
PT-2026-43329
Name of the Vulnerable Software and Affected Versions Starlette versions prior to 1.0.1 Description Starlette, a lightweight ASGI Asynchronous Server Gateway Interface framework, fails to validate the HTTP Host request header before using it to reconstruct request.url. While the routing algorithm...