mastyf.ai

mastyf.ai Perimeter security for your AI. Runtime enforcement, policy control, and full audit trail for every AI action. Website · Quick start · Policy · Dashboard · GitHub The problem AI agents can read your files, push code, query databases, execute shell commands, and call external APIs. They ...

tetragon

Cilium의 새로운 Tetragon 구성 요소는 강력한 실시간 eBPF 기반 보안 관찰 가능성 및 런타임 시행을 가능하게 합니다. Tetragon은 다음과 같은 보안상 중요한 이벤트를 감지하고 대응할 수 있습니다: 프로세스 실행 이벤트 시스템 호출 활동 네트워크 및 파일 액세스를 포함한 I/O 활동 Kubernetes 환경에서 사용될 때 Tetragon은 Kubernetes 인식형입니다. 즉, 네임스페이스, 파드 등의 Kubernetes ID를 이해하므로, 개별 워크로드와 관련하여 보안 이벤트 감지를 구성할 수 있습니다...

CVE-2026-27002

OpenClaw is a personal AI assistant. Prior to version 2026.2.15, a configuration injection issue in the Docker tool sandbox could allow dangerous Docker options bind mounts, host networking, unconfined profiles to be applied, enabling container escape or host data access. OpenClaw 2026.2.15 block...

CVE-2026-27002 OpenClaw: Docker container escape via unvalidated bind mount config injection

OpenClaw is a personal AI assistant. Prior to version 2026.2.15, a configuration injection issue in the Docker tool sandbox could allow dangerous Docker options bind mounts, host networking, unconfined profiles to be applied, enabling container escape or host data access. OpenClaw 2026.2.15 block...

PT-2026-20964

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.2.15 Description A configuration injection issue in the Docker tool sandbox could allow dangerous Docker options bind mounts, host networking, unconfined profiles to be applied, potentially enabling container...

One RNG to Rule Them All: How Randomness Becomes an Attack Vector in Machine Learning

Machine learning relies on randomness as a fundamental component in various steps such as data sampling, data augmentation, weight initialization, and optimization. Most machine learning frameworks use pseudorandom number generators as the source of randomness. However, variations in design choic...

Toxic_Flow_Analysis_Framework_For_Agentic_AI

Toxic Flow Analysis TFA Framework A Secure-by-Design framew...

Trust in LLM-Controlled Robotics: A Survey of Security Threats, Defenses and Challenges

The integration of Large Language Models LLMs into robotics has revolutionized their ability to interpret complex human commands and execute sophisticated tasks. However, such paradigm shift introduces critical security vulnerabilities stemming from the ''embodiment gap'', a discord between the...

Securing Mixed Rust with Hardware Capabilities

The Rust programming language enforces three basic Rust principles, namely ownership, borrowing, and AXM Aliasing Xor Mutability to prevent security bugs such as memory safety violations and data races. However, Rust projects often have mixed code, i.e., code that also uses unsafe Rust, FFI Forei...

Fides Security Vulnerabilities

Fides is an open source privacy engineering platform for managing the implementation of data privacy requests in a runtime environment and the enforcement of privacy regulations in code. A security vulnerability exists in Fides version 2.11.0 and later. An attacker exploiting this vulnerability...

SUSE CVE-2006-7216

Apache Derby before 10.2.1.6 does not determine privilege requirements for lock table statements at compilation time, and consequently does not enforce privilege requirements at execution time, which allows remote authenticated users to lock arbitrary tables...

KubeArmor - Container-aware Runtime Security Enforcement System

Introduction to KubeArmor KubeArmor is a container-aware runtime security enforcement system that restricts the behavior such as process execution, file access, networking operation, and resource utilization of containers at the system level. KubeArmor operates with Linux security modules LSMs,...