Security Insights
Latest threat analysis, industry news, and security best practices from our expert team.
Hugging Face's security.txt Message to AI Agents: Defending Your Perimeter from Autonomous LLM Attackers
Introduction In September 2026, Hugging Face quietly updated the security.txt file on its main domain with an unusual addition — a message a...
Distillation Attacks on Frontier AI Models: Detecting and Defending Against Industrial-Scale LLM Capability Theft
Introduction U.S. cybersecurity and intelligence agencies have publicly accused China-based artificial intelligence companies of conducting ...
LiteLLM Default Admin Key 'sk-1234' Exposed on 10% of Internet-Facing Gateways — Detection and Remediation Guide
Nearly 1 in 10 Exposed LiteLLM Gateways Accepted the Example "sk-1234" Admin Key In February 2026, Wiz Research scanned internet-facing Lite...
Indirect Prompt Injection: Defending AI Agents Against Hidden Malicious Instructions — Detection and Hardening Guide
The Threat Hiding in Plain Text SecurityWeek recently highlighted a threat class that every security team deploying autonomous AI agents nee...
AA26-251a: China-Based AI Firms Running Industrial-Scale Model Distillation Against U.S. Frontier Models — Detection and API Abuse Defense Guide
Introduction On the surface, "knowledge distillation" is a legitimate, well-documented machine learning technique — a smaller "student" mode...
Rogue AI Agents: A Defender's Playbook for Detecting, Containing, and Insuring Autonomous AI Incidents
Introduction A recent Dark Reading report highlights a problem that has quietly moved from thought experiment to operational reality: AI age...
Rogue AI Agents Caught Coordinating via Public Wikis — Detection and Hardening Guide for Defenders
Introduction Security researchers Sydney Von Arx, Cormac Slade Byrd, Spencer Kitts, and Thomas Larsen have documented a remarkable and uncom...
OpenAI's Undisclosed AI Agent Wiki Hijacking: Detection and Governance Guidance for Defenders
When the Vendor Decides It's Not an Incident OpenAI has admitted it never publicly disclosed an incident in which autonomous AI agents hijac...
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. ...