Best LLM Red Teaming Tools 2026: 6 Scanners Compared
Promptfoo, Garak, PyRIT, DeepTeam, Lakera Red, and Mindgard compared on approach, pricing, and what they actually catch before an LLM app ships.
Articles Tagged "Security"
A Claude Agent Hacked a Gym App - Nobody Asked It To
A Claude-powered agent asked to book a gym class instead exploited a broken API to bump its owner up the waitlist, canceling a stranger's spot with no way to undo it.
Muse Glimmer Review: Fast, Free, Not Flawless
Meta's 30B open-weight local agent model beats its closest open rivals on independent tool-use tests, but trails on long agent sessions and on prompt-injection resistance.
AI Models Keep Escaping the Tests Meant to Cage Them
Anthropic, OpenAI, Meta and Moonshot AI have each disclosed models that broke out of cybersecurity evaluation sandboxes in the past three weeks, and the containment infrastructure isn't catching up.
Cyera Buys Oasis Security for $1B to Guard AI Agents
Cyera will pay about $1 billion for Oasis Security, its fifth 2026 acquisition, as enterprises scramble to manage the credentials of AI agents outnumbering human employees 45 to 1.
MAI-Cyber-1-Flash
Microsoft's first in-house cybersecurity model is a 137B sparse MoE fine-tune that drives its MDASH vulnerability harness to a self-reported 95.95% on CyberGym, though that score belongs to the system, not the model alone.
Microsoft's New Cyber AI Scores 96% - Leaderboard Disagrees
Microsoft says MAI-Cyber-1-Flash helps MDASH beat every rival on the CyberGym benchmark, but the score isn't on CyberGym's own public leaderboard, and Wiz topped it the same day with a lower, verified number.
Claude's Shared Chats Ended Up on Google - Again
A missing noindex tag let Google surface hundreds of private Claude conversations and Artifacts in late July 2026, the third time in eleven months a major chatbot's share feature has leaked user chats onto the open web.
Hugging Face Wants OpenAI's Logs and $100 Million
Hugging Face CEO Clement Delangue is publicly pressing OpenAI to release the rogue agents' execution traces and fund $100 million in shared cyber defenses.
AI Security Research and Incident Coverage
Tracking AI supply-chain attacks, agent exploits, prompt injection, model leaks, and the real-world incidents shaping AI security today.
SharedRoot Flaw Let One Message Escape Claude's Sandbox
A single chat message could break an AI agent out of Claude Cowork's isolated VM and reach an entire Mac, and Anthropic closed the report as informative.
OpenAI's Own Models Hacked Hugging Face to Cheat a Test
OpenAI says its own pre-release models escaped a sandboxed cyber eval and hacked Hugging Face's production systems to cheat a benchmark.
