Security & Safety
IBM and Red Hat Put $5B Behind Lightwell for AI-Era Patching
IBM and Red Hat introduced Project Lightwell, a $5B effort to turn AI-found open-source vulnerabilities into verified patches.
← All categories
Security & Safety
Vulnerabilities, prompt injection, model safeguards, and containment design.
Security & Safety
Anthropic sabotage report puts agent monitoring on trial
Anthropic’s Opus 4 sabotage risk report shows why coding agents need audit trails across logs, pull requests, security events, and external review.
Security & Safety
NSA MCP guidance warns about GitHub scope, WhatsApp leaks, and agent runtime risk
NSA published MCP security design guidance for AI-driven automation, turning tool permissions, tokens, logs, sandboxing, DLP, and scans into deployment requirements.
Security & Safety
Chrome Enterprise MCP turns browser security policy into agent tools
Google released a Chrome Enterprise Premium MCP server that exposes DLP rules, connector policy, browser telemetry, and activity logs to AI agents.
Security & Safety
OpenAI launches Rosalind Biodefense as a trusted-access test for GPT-Rosalind
OpenAI has launched Rosalind Biodefense, pairing GPT-Rosalind, Codex life-science tooling, and trusted access for public-health defense work.
Security & Safety
Arm open-sources Metis, a security agent aimed at SAST false positives
Arm has open-sourced Metis, an agentic AI security framework for code review, SARIF triage, evidence chains, and lower false-positive cost.
Security & Safety
AI Passed the CAPTCHA, but 0.88 AUC Caught the Process
Roundtable and an arXiv paper argue that AI agents can match CAPTCHA answers while still revealing themselves through click order and behavior.
Security & Safety
Claroty Claire Launches With Approval Boundaries for Factory and Hospital AI Security
Claroty introduced Claire, a CPS-native AI security agent. The launch shows why AI action in factories and hospitals has to be tied to asset data, approvals, and audit trails.
Security & Safety
Codex Can Reach Internal MCP Servers Through OpenAI Secure Tunnels
OpenAI Secure MCP Tunnel gives ChatGPT, Codex, Responses API, and AgentKit an outbound-only path to private MCP servers without public endpoints.
Security & Safety
Mythos reached ACE on 21 of 41 V8 bugs, Anthropic exploit benchmarks warn defenders
Anthropic published Claude Mythos Preview exploit evaluations and a CVD dashboard. V8 21/41 ACE and 1,596 disclosed flaws reset security triage expectations.
Security & Safety
Anthropic published Claude containment details, and 24 AWS key thefts explain the risk
Anthropic detailed the isolation design behind Claude Code and Claude Cowork. The numbers turn agent security from approval prompts into sandbox, VM, and egress policy.
Security & Safety
YouTube Will Auto-Label AI Videos as Detection Moves to the Platform
YouTube is moving AI-generated video labels onto the player surface and adding automatic detection for realistic AI media. Here is what changes for creators, viewers, and AI product teams.