93 matches found
ws4-secure-design-agentic-systems
CoSAI 工作流 4：代理系统的安全设计模式 此仓库用于 CoSAI 工作流 4（代理系统的安全设计模式）的工作。CoSAI 是 OASIS 开放项目，也是一个由业界领先组织的 AI 和安全专家组成的开放生态系统，致力于分享安全 AI 部署的最佳实践，并合作开展 AI 安全研究和产品开发。有关 CoSAI 的更多信息，请访问 CoSAI 网站 和 开放项目仓库，其中包含有关治理、赞助商、名册和项目章程的信息。 关于本工作流 本工作流的目标是研究和开发基于 AI 的代理系统的安全设计模式，包括对 AI...
oasis
OASIS 进攻性AI安全智能标准 — 开源AI安全基准测试。 基准测试AI模型执行进攻性安全任务的能力——漏洞发现、利用、权限提升等。完整分析包含MITRE ATT&CK映射、行为评分和详细报告。所有操作在本地运行，使用您自己的API密钥。无需注册，数据不会离开您的机器。 为什么选择OASIS？ AI模型在进攻性安全方面的能力日益增强。我们需要可重现、透明的可视化方式了解它们的表现——不是在关闭的门后，而是在安全社区可以验证、贡献和改进的开放环境中。 OASIS提供： 标准化挑战 在Docker容器中（CTF风格，隔离，可重现） 多提供商基准测试...
Pribado
🔐 Pribado Gestión Privada de Claves API e Infraestructura de Conocimiento Cero Pribado es una plataforma auto-alojable y de conocimiento cero para gestionar claves API, secretos cifrados y comunicaciones privadas. Construido sobre Oasis Sapphire para computación confidencial respaldada por...
CCR: Towards a Common, Quality-Gated CACAO Integrations Registry for European Cybersecurity Automation
Standardised, machine-readable cybersecurity playbooks provide a basis for portable, shareable, and reusable incident-response logic. OASIS CACAO provides a vendor-neutral representation for such playbooks, but not the product-specific integration artefacts needed to invoke external products and...
The like Trap: Multi-Stage Poisoning against Agents in Similarity-Based Recommendation Systems
With recent advancements in large language models LLMs and LLM-based agents, these agents are becoming increasingly autonomous and gaining broader access to act on users' behalf on the internet. However, the vulnerability of automated agents deployed on social media platforms e.g., for managing a...
ClawJacked Vulnerability in OpenClaw Could Let Websites Hijack AI Agents
Is your AI assistant safe? Oasis Security researchers have found a critical ClawJacked vulnerability in OpenClaw that allows hackers to hijack AI agents through a simple browser tab...
Malicious code in oasis-os-provider-messaging (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector cca1eb9a5a42a34b2db68e6d23c9c2cd2cbe7098f742e647c9c6867b342e95ab The package oasis-os-provider-messaging was found to contain malicious code...
EUVD-2026-4525
Malicious code in oasis-os-provider-messaging npm...
MAL-2026-481 Malicious code in oasis-os-provider-messaging (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector cca1eb9a5a42a34b2db68e6d23c9c2cd2cbe7098f742e647c9c6867b342e95ab The package oasis-os-provider-messaging was found to contain malicious code...
Lvzhou CMS 安全漏洞
Lvzhou CMS Oasis CMS is a content management system by wanliofficial individual developer. A security vulnerability exists in Lvzhou CMS Oasis CMS, which stems from the unfiltered direct splicing of SQL queries in the title parameter of the ContentService, which may lead to SQL injection attacks...
EUVD-2020-0385
Malware in sbrugna...
EUVD-2020-5378
Malware in sbrugna...
Malicious code in oasis-59qsj-xdrzi-jade-project (npm)
The package oasis-59qsj-xdrzi-jade-project was found to contain malicious code...
Malicious code in oasis-auo12-4wf7d-cascade-project (npm)
The package oasis-auo12-4wf7d-cascade-project was found to contain malicious code...
Malicious code in oasis-ivory-tpq806-project (npm)
The package oasis-ivory-tpq806-project was found to contain malicious code...
Malicious code in oasis-kj0dc-r42bz-glow-project (npm)
The package oasis-kj0dc-r42bz-glow-project was found to contain malicious code...
Malicious code in oasis-q3an5-xfmxa-nymph-project (npm)
The package oasis-q3an5-xfmxa-nymph-project was found to contain malicious code...
Malicious code in oasis-wallet (npm)
The package oasis-wallet was found to contain malicious code...