🔐 Capability Systems - matmat · Scour

Evaluating Privilege Usage of Agents on Real-World Tools 🔒WASM Capabilities

arxiv.org·2d·

Claude Mythos Wake-Up Call: What AI Vulnerability Discovery Means for Cyber Defense 🎯Threat Hunting

blog.checkpoint.com·15h·

paolovella/vellaveto: Agentic security control plane for MCP and AI agent tool calls. MCP-native policy gateway with topology discovery and audit. 📦Container Security

github.com·4d·Hacker News·

Alcazar Security: Dead man's switch and digital legacy ⏳Time Capsule Networks

alcazarsec.com·22h·Hacker News·

A Taxonomy of Cognitive Security 🔐Quantum Security

schneier.com·1d·schneier.com·

K8s security with graph-based attack paths (like Wiz, but affordable) 📦Container Security

juliet.sh·6d·Hacker News·

A Personal AI Assistant, Built Secure 🔒WASM Capabilities

ironcurtain.dev·1d·Hacker News·

How to Categorize AI Agents and Prioritize Risk 🎯Threat Hunting

bleepingcomputer.com·1d·

Strategic Decisions for CISOs: Part 2: Why Deployment Strategy Just Became Strategic 🖥️Self-hosted Infrastructure

vmray.com·5d·

Applying security fundamentals to AI: Practical advice for CISOs 🎯Threat Hunting

microsoft.com·1d·

The Zero-Code Security Team: Shifting Left with Prompt-Native AI Agents 🔒WASM Capabilities

godaddy.com·2d·Hacker News·

Sandboxing AI Agents, Trivy Compromised, Pentesting AWS' AI Pentester 🏠Homelab Pentesting

tldrsec.com·6d·

Preparing for agentic AI: A financial services approach 🎯Threat Hunting

aws.amazon.com·6d·

The Computer System Trail 💾Persistence Strategies

arxiv.org·1d·

msaleme/red-team-blue-team-agent-fabric: 342-test security harness for autonomous AI agents. MCP, A2A, x402/L402, AIUC-1 pre-cert, NIST AI 800-2 aligned. 97.9% production-validated. pip install agent-security-harness 🏠Homelab Pentesting

github.com·1d·Hacker News·

Strategic Decisions for CISOs: Part 1: The Core Competence Missing in Email, EDR and Threat Intel 🎯Threat Hunting

vmray.com·5d·

Security and Privacy in Virtual and Robotic Assistive Systems: A Comparative Framework ✋Tactile Computing

arxiv.org·1d·

cisco-ai-defense/defenseclaw: Security Governance for Agentic AI ⚡Proof Automation

github.com·3d·Hacker News·

Design Principles for the Construction of a Benchmark Evaluating Security Operation Capabilities of Multi-agent AI Systems 🎯Threat Hunting

arxiv.org·1d·

SkillTester: Benchmarking Utility and Security of Agent Skills ⚡Proof Automation

arxiv.org·1d·

Loading more...