9 matches found
skill-scanner
Skill Scanner A best-effort security scanner for AI Agent Skills that detects prompt injection, data exfiltration, and malicious code patterns. It combines pattern-based detection YAML + YARA-X, AST and dataflow analysis , an optional LLM-as-a-judge , and a bounded CEL decision layer over typed...
fas-judgement-oss
FAS Judgement 提示注入攻击控制台 在别人之前测试你的AI防御。 安装 | 游戏模式 | 全球排行榜 | 演示目标 | 功能 | 精英版 | 贡献 为什么选择 Judgement？ 你的AI聊天机器人、API或智能体很可能存在提示注入漏洞。大多数都是这样。问题是，大多数团队没有适当的工具或专业知识来测试这一点。 Judgement为你提供了一种结构化的方法，可以将分类的攻击模式对准任何AI端点，并精确查看哪些地方出了问题。无需安全背景——内置的游戏模式会边玩边教你。 由Fallen Angel...
c4-meta-system
C4-META System v1.0.0 prototipo de investigación Prototipo de investigación para la defensa multicapa de IA: explicabilidad C4, clasificadores ensemble, desofuscación, motor de seguridad O₂, defensa ThoughtVirus y alineación de valores SVETILO. Grado alfa: validado internamente, auditoría externa...
skill-scanner v2.0.14
Skill Scanner A best-effort security scanner for AI Agent Skills that detects prompt injection, data exfiltration, and malicious code patterns. It combines pattern-based detection YAML + YARA-X, AST and dataflow analysis , an optional LLM-as-a-judge , and a bounded CEL decision layer over typed...
Skill Scanner 安全漏洞
Skill Scanner is an open-source security scanner developed by Cisco AI Defense. Versions of Skill Scanner 1.0.1 and earlier contain security vulnerabilities. These vulnerabilities stem from incorrect binding of the API server to multiple interfaces, which may lead to denial-of-service attacks or...
Microsoft named an overall leader in KuppingerCole Leadership Compass for Generative AI Defense
Today, we are proud to share that Microsoft has been recognized as an overall leader in the KuppingerCole Leadership Compass for Generative AI Defense GAD, an independent report from a leading European analyst firm. This recognition reinforces the work we’ve been doing to deliver enterprise-ready...
ThreatsDay Bulletin: CarPlay Exploit, BYOVD Tactics, SQL C2 Attacks, iCloud Backdoor Demand & More
From unpatched cars to hijacked clouds, this week’s Threatsday headlines remind us of one thing — no corner of technology is safe. Attackers are scanning firewalls for critical flaws, bending vulnerable SQL servers into powerful command centers, and even finding ways to poison Chrome’s settings t...
Eliminating AI Deepfake Threats: Is Your Identity Security AI-Proof?
Artificial Intelligence AI has rapidly evolved from a futuristic concept to a potent weapon in the hands of bad actors. Today, AI-based attacks are not just theoretical threats—they're happening across industries and outpacing traditional defense mechanisms. The solution, however, is not...
Unveiling the 2024 Imperva DDoS Threat Landscape Report
In the ever-changing landscape of cybersecurity, Distributed Denial of Service DDoS attacks continue to be a significant threat. To help organizations stay ahead, were excited to introduce the 2024 Imperva DDoS Threat Landscape Report. This comprehensive report offers a deep dive into DDoS attack...