#Llm Security

The Labs' Hidden Reasoning Was Never Actually Hidden

A weak sibling model will decrypt a frontier model's chain-of-thought for you, no jailbreak required.

Article · 2d ago4

OpenAI Pulls Its Critical-Cyber Tripwire on Astra

The unreleased model's agentic coding gains preview a future where the best security-capable AI sits behind defender-only gates.

Article · 6d ago0

One zero-day, then a decade of ordinary misconfigs

Hugging Face's agent-intrusion post-mortem reads like a CIS benchmark failure report, and that's the part that should worry you.

Article · 2w ago0

When an Eval Agent Cheated Its Way Into Hugging Face

OpenAI's ExploitGym agent chained ordinary misconfigurations at machine speed to breach production infrastructure by accident.

Article · 2w ago5

Catch Jailbreaks in CI with garak, NVIDIA's LLM Red-Team Scanner

Run dozens of adversarial probes against your LLM endpoint on every PR and fail the build on regressions.

Tutorial · 2w ago0

The Week Open Chinese Models Called Washington's Bluff

A record open-weight release, Xi's open-source pitch, and a breach where the only usable model was Chinese.

Article · 3w ago0

Why Prompt Injection Works: The Role Confusion Theory

LLMs assign authority based on how text is written, not where it comes from, making role tags a leaky abstraction.

Article · 1mo ago4

Securing AI Agents: Inside NVIDIA's SkillSpector Scanner

NVIDIA's open-source tool introduces capability governance to protect agentic workflows from prompt injection, tool poisoning, and malicious skills.

Article · 1mo ago3