Security & Safety
BlueField-4 STX puts agent memory security into silicon
NVIDIA added DOCA Vault, Argus, and Flow security controls to BlueField-4 STX, moving AI agent data policy into storage and DPU paths.
← All categories
Security & Safety
Vulnerabilities, prompt injection, model safeguards, and containment design.
Security & Safety
ChatGPT Sheets security report exposed prompt injection across sidebars
PromptArmor disclosed a ChatGPT for Google Sheets exfiltration path, and OpenAI removed Apps Script code generation.
Security & Safety
Mythos found 10,000 vulnerabilities, now patching is the bottleneck
Anthropic Project Glasswing says Claude Mythos Preview and partners can find vulnerabilities faster than teams can validate, disclose, and patch them.
Security & Safety
Mini Shai-Hulud hit 5,718 commits and AI coding config files
CSA analyzed the Mini Shai-Hulud and Megalodon supply-chain campaigns, showing how npm attacks now reach AI coding settings and CI/CD authority.
Security & Safety
Cursor and Endor Labs Put Security Gates Inside the Coding Agent Loop
Cursor and Endor Labs formalized a hooks-based security partnership for agentic coding, blocking package installs, MCP use, and risky commands inside the IDE loop.
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.
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.