sec-gemini

Sec-Gemini SDK 및 CLI 이 저장소는 Google의 실험적인 사이버보안 특화 AI인 Sec-Gemini용 SDK와 CLI를 제공합니다. SDK 다음 플랫폼용 SDK를 사용할 수 있습니다: Python은 sec-gemini-python/에 있습니다. TypeScript는 sec-gemini-ts/에 있습니다. 또한 웹사이트에 쉽게 통합할 수 있는 웹 컴포넌트도 있습니다. 로드하는 방법은 다음과 같습니다: CLI CLI는 Linux와 macOS에 설치할 수 있습니다: curl --proto '=https'...

cai

사이버보안 AI CAI 프로페셔널 에디션무제한 alias1 토큰 | 📊 벤치마크 보기 | 🚀 자세히 알아보기 🔓 커뮤니티 에디션 연구 및 학습 · 연구자와 학생에게 완벽함 pip install cai-framework ✅ 연구용 무료 🤖 300개 이상의 AI 모델 🌍 커뮤니티 주도 📚 오픈소스 🔧 확장 가능한 프레임워크 🚀 프로페셔널 에디션 엔터프라이즈 및 프로덕션 · 월 €350 · 무제한 alias1 토큰 → PRO로 업그레이드 ⚡ alias1 모델 - ∞ 무제한 토큰 🚫 거부 없음 - 제한 없는 AI 🏆 CTF 벤치마크에...

PYSEC-2026-303 CAI find_file Agent Tool has Command Injection Vulnerability Through Argument Injection

Summary The CAI Cybersecurity AI framework contains multiple argument injection vulnerabilities in its function tools. User-controlled input is passed directly to shell commands via subprocess.Popen with shell=True, allowing attackers to execute arbitrary commands on the host system. Vulnerable...

Cybersecurity AI (CAI) Framework 0.5.10 - Command Injection

Exploit Title: Cybersecurity AI CAI Framework 0.5.10 - Command Injection CVE: CVE-2026-25130 Date: 2026-02-03 Exploit Author: Mohammed Idrees Banyamer Author Country: Jordan Instagram: @banyamersecurity Author GitHub: https://github.com/yourusername Vendor Homepage:...

CVE-2026-25130

Cybersecurity AI CAI is a framework for AI Security. In versions up to and including 0.5.10, the CAI Cybersecurity AI framework contains multiple argument injection vulnerabilities in its function tools. User-controlled input is passed directly to shell commands via subprocess.Popen with...

CVE-2026-25130

Cybersecurity AI CAI is a framework for AI Security. In versions up to and including 0.5.10, the CAI Cybersecurity AI framework contains multiple argument injection vulnerabilities in its function tools. User-controlled input is passed directly to shell commands via subprocess.Popen with...

GHSA-JFPC-WJ3M-QW2M CAI find_file Agent Tool has Command Injection Vulnerability Through Argument Injection

Summary The CAI Cybersecurity AI framework contains multiple argument injection vulnerabilities in its function tools. User-controlled input is passed directly to shell commands via subprocess.Popen with shell=True, allowing attackers to execute arbitrary commands on the host system. Vulnerable...

CVE-2026-25130 Cybersecurity AI vulnerable to command Injection through argument injection in find_file Agent tool

Cybersecurity AI CAI is a framework for AI Security. In versions up to and including 0.5.10, the CAI Cybersecurity AI framework contains multiple argument injection vulnerabilities in its function tools. User-controlled input is passed directly to shell commands via subprocess.Popen with...

CVE-2026-25130

CVE-2026-25130 affects the Cybersecurity AI (CAI) framework up to version 0.5.10. The vulnerability is in the find_file() tool (src/cai/tools/reconnaissance/filesystem.py): user-controlled input is concatenated into a shell command using a plain f-string and run via shell=True, enabling argument ...

CVE-2026-25130 Cybersecurity AI vulnerable to command Injection through argument injection in find_file Agent tool

Cybersecurity AI CAI is a framework for AI Security. In versions up to and including 0.5.10, the CAI Cybersecurity AI framework contains multiple argument injection vulnerabilities in its function tools. User-controlled input is passed directly to shell commands via subprocess.Popen with...

CVE-2026-25130 Cybersecurity AI vulnerable to command Injection through argument injection in find_file Agent tool

Cybersecurity AI CAI is a framework for AI Security. In versions up to and including 0.5.10, the CAI Cybersecurity AI framework contains multiple argument injection vulnerabilities in its function tools. User-controlled input is passed directly to shell commands via subprocess.Popen with...

CVE-2026-25130

Cybersecurity AI CAI is a framework for AI Security. In versions up to and including 0.5.10, the CAI Cybersecurity AI framework contains multiple argument injection vulnerabilities in its function tools. User-controlled input is passed directly to shell commands via subprocess.Popen with...

CVE-2026-25130: Improper Neutralization of Special Elements used in an OS Command

Cybersecurity AI CAI is a framework for AI Security. In versions up to and including 0.5.10, the CAI Cybersecurity AI framework contains multiple argument injection vulnerabilities in its function tools. User-controlled input is passed directly to shell commands via subprocess.Popen with...

Cybersecurity AI operating system command injection vulnerabilities

Cybersecurity AI is an open-source network security AI framework developed by Alias Robotics. Versions of Cybersecurity AI prior to 0.5.10 contain a vulnerability related to operating system command injection. This vulnerability stems from parameter injections in multiple function tools, which ma...

PT-2026-5441

Name of the Vulnerable Software and Affected Versions Cybersecurity AI CAI versions up to and including 0.5.10 Description The Cybersecurity AI CAI framework contains multiple argument injection vulnerabilities within its function tools. User-controlled input is directly passed to shell commands...

Towards Cybersecurity Superintelligence: From AI-Guided Humans to Human-Guided AI

Cybersecurity superintelligence -- artificial intelligence exceeding the best human capability in both speed and strategic reasoning -- represents the next frontier in security. This paper documents the emergence of such capability through three major contributions that have pioneered the field o...

CVE-2025-67511

Cybersecurity AI CAI is an open-source framework for building and deploying AI-powered offensive and defensive automation. Versions 0.5.9 and below are vulnerable to Command Injection through the runsshcommandwithcredentials function, which is available to AI agents. Only password and command...

Cybersecurity AI 命令注入漏洞

Cybersecurity AI is an open source cybersecurity AI security framework from Alias Robotics. A command injection vulnerability exists in Cybersecurity AI version 0.5.9 and earlier, which stems from a command injection in the runsshcommandwithcredentials function that could lead to the execution of...

CVE-2025-67511: Improper Neutralization of Special Elements used in a Command

Cybersecurity AI CAI is an open-source framework for building and deploying AI-powered offensive and defensive automation. Versions 0.5.9 and below are vulnerable to Command Injection through the runsshcommandwithcredentials function, which is available to AI agents. Only password and command...

CVE-2025-67511 Cybersecurity AI (CAI) vulnerable to Command Injection in run_ssh_command_with_credentials Agent tool

Cybersecurity AI CAI is an open-source framework for building and deploying AI-powered offensive and defensive automation. Versions 0.5.9 and below are vulnerable to Command Injection through the runsshcommandwithcredentials function, which is available to AI agents. Only password and command...