Security Insights
Latest threat analysis, industry news, and security best practices from our expert team.
Cohere Finds Qwen AI Model Contacting a Server in China — Detecting and Blocking Unexpected Egress from Self-Hosted LLMs
Cohere Flags Qwen Model for Unexpected Outbound Contact — What Defenders Need to Do About It Cohere's research team has published a finding ...
llm-anthropic 0.29 Released: What Security Teams Must Do to Govern LLM CLI Tooling and Anthropic API Access
Introduction Simon Willison has released version 0.29 of llm-anthropic, the plugin that connects his widely used llm command-line tool to An...
llm-typesafe 0.1a0: Enforcing Type-Safe LLM Outputs — What Security Teams Should Know Before Adopting Pre-Alpha AI Tooling
Introduction Simon Willison — creator of the widely used llm CLI tool and datasette — has released llm-typesafe 0.1a0, an alpha-stage plugin...
Beijing Responds to Anthropic CEO's Call to Curb Chinese AI: What the AI Geopolitical Escalation Means for Enterprise Defenders
Introduction China's Ministry of Foreign Affairs has publicly pushed back against Anthropic CEO Dario Amodei's recent essay calling for curb...
AI Supply Chain Under Attack: Defending Against Malicious Open-Source Models and Packages in 2026
The AI Supply Chain Problem Is No Longer Theoretical Pierluigi Paganini's Security Affairs newsletter Round 594 puts its finger on something...
Hawley Probe of OpenAI Over Hugging Face Breach: Defending Against AI Supply Chain and Token Exposure Risk
Congressional Scrutiny Meets a Real Defensive Problem Senator Josh Hawley (R-MO) has opened an inquiry into OpenAI following the Hugging Fac...
Nvidia's $13B Hugging Face Acquisition: Securing the Open-Source AI Model Supply Chain After Consolidation
Introduction Nvidia has announced its intent to acquire Hugging Face — the de facto central repository for open-source AI models, datasets, ...
llm-gemini 0.34 and Gemini 3.8 Flash: A Defender's Guide to Safely Adopting LLM CLI Tooling in Security Operations
Introduction On September 2, 2026, Simon Willison released llm-gemini 0.34, the Gemini plugin for his widely used llm command-line toolkit. ...
Hugging Face Supply-Chain Attack & PHANTOM-B: Threat Modeling Lessons for Defending AI/ML Pipelines
Introduction When Adam Shostack — arguably the most authoritative voice in threat modeling alive — says he was "blown away" by an attack dis...