AI Security

Swarm traces: how OpenAI agents hacked Hugging Face Byte

Early rogue AI agent activity and attempts to hack found on urlquery.net Byte

Insights from table-top exercises in Europe on AI safety and cyber misuse Byte

VMs Won't Contain Cyber-Capable Agents Byte

Beyond Chat: Building Multi Agent SOC Ecosystems with Claude and Google MCP Byte

SANS VulnOps Field Guide for when tickets can't keep up Byte

OpenAI agents carried out an undisclosed cyber-attack on RubyGems Byte

Discovery of a new OpenAI agent message board Byte

The Vulnpocalypse Report: An Analysis Byte

Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident Byte

Testing Claude Mythos Preview For Code Security Byte

Antares: Small Models for Vulnerability Localization Byte

The CVE System Meets the AI Firehose Byte

CVE-2026-LGTM: Seven Scanners, One Honeypot Byte

Orchestration Has No ATT&CK ID 5 min read

MITRE ATT&CK can tell you an attacker dumped credentials (T1003) and moved laterally over SSH (T1021). It cannot tell you those two steps were chosen, sequenced, and executed by an AI agent with …

Behind the LLM Cybersecurity Hype 4 min read

The same vendors publishing breakthrough numbers on LLM cyber capability are publishing the disclaimers in the same posts. Read both halves and the picture changes.

The Kernel's New Rules for AI Bug Reports 3 min read

When Linus Torvalds released Linux 7.1-rc4 on May 17, he flagged a documentation update as the highlight. The substance is a policy: the kernel’s security workflow is being restructured to cope …

The AI-Assisted Breach of Mexico's Government Infrastructure Byte

Anthropic's Claude Mythos Preview finds thousands of unknown flaws Byte

Benchmarking Self-Hosted LLMs for Offensive Security Byte

How we made Trail of Bits AI-native (so far) Byte

Vulnerability Spoiler Alert flags security fixes before the CVE Byte

Anthropic's red team and Mozilla find 22 Firefox CVEs with Claude Byte

LLM agents wrote over 40 QuickJS exploits for Sean Heelan Byte

CVE-2025-15467 - AISLE found all 12 OpenSSL January 2026 CVEs Vulnerability