Brex has open-sourced CrabTrap, an HTTP proxy that uses an LLM-as-a-judge architecture to intercept, evaluate, and block or allow requests made by AI agents in real time against configurable policies. …
Firefox CTO Bobby Holley reports that a collaboration with Anthropic using an early version of Claude Mythos Preview identified 271 vulnerabilities in Firefox, resulting in fixes shipped in Firefox …
Simon Willison has created a git-based tool to track the evolution of Anthropic's publicly published Claude system prompts across model versions, enabling structured diff analysis of prompt changes …
GoModel is an open-source AI gateway written in Go that provides a unified OpenAI-compatible API across multiple LLM providers including OpenAI, Anthropic, Gemini, Groq, xAI, and Ollama. As an …
Anthropic's published system prompt diff between Claude Opus 4.6 and 4.7 reveals significant expansions in agentic tool access, autonomous browsing capabilities, and child safety guardrails — changes …
Vercel suffered a breach originating from a compromised third-party AI tool, Context.ai, where an employee's OAuth token was hijacked to access Vercel's Google Workspace and internal environment …
Bruce Schneier analyses Anthropic's Claude Mythos Preview and Project Glasswing, a controlled deployment programme aimed at finding and patching software vulnerabilities before the model is publicly …
Artemis, a cybersecurity startup focused on AI-powered threat defence, has emerged from stealth with $70 million in funding, positioning itself to counter AI-driven attacks across applications, users, …
A North Korean threat group (UNC1069) compromised the popular npm Axios library via a supply chain attack, injecting a backdoor (WAVESHAPER.V2) into two poisoned versions that were inadvertently …
The article argues that AI's primary security risk lies not in introducing entirely new vulnerability classes, but in dramatically amplifying the impact and exploitability of well-established ones. …
A chained vulnerability in Cursor AI—a widely-used AI-powered code editor—allowed attackers to combine indirect prompt injection with a sandbox escape and the application's built-in remote tunnel …
OpenAI has expanded access to GPT-5.4-Cyber, a fine-tuned model designed for defensive cybersecurity applications, following Anthropic's reveal of its Mythos cybersecurity model. While framed as a …
CrowdStrike has announced a partnership with OpenAI's Threat Actor Collaboration (TAC) programme, positioning frontier AI models as defensive tools within the cybersecurity operations space. The …
The article examines the architectural tension between fully agentic AI systems and deterministic validation frameworks in security testing contexts, arguing that unconstrained AI autonomy introduces …
Capsule Security, an Israeli startup, has emerged from stealth with $7 million in seed funding focused on runtime security for AI agents, continuously monitoring their behaviour to detect and prevent …