Forever Security Says Planted AGENTS.md and CLAUDE.md Files in ~/Downloads Steered Codex and Claude Code, but Its Report Names No Versions, Run Counts or Permission Modes
Forever Security says instruction files dropped into ~/Downloads...
Browse Tag
AI Agent Security
10 Articles
Docker’s YOLO Mode Explainer Turns Agent Permissions Into a Boundary Problem
Docker's new explainer names YOLO mode, the habit of...
Docker’s 17,600-Action Math Turns AI Agent Security Into a Systems Problem
Docker's read on the OpenAI/Hugging Face breach argues that...
Docker’s Sandboxes Turn AI Agent Hardware Access Into a Network Problem
Docker's new ESP32 firmware guide reuses a 1997 network-serial...
How to Isolate Per-User OAuth Tokens for a Multi-User AI Agent With Python and Ollama
Learn how to give a multi-user AI agent per-user OAuth access to...
The Nx Supply-Chain Attack Turned AI Coding Agents Into Credential Scanners
A Docker case study revisits the Nx npm attack that turned...
Red Hat’s OpenShift Sandboxed Containers Turn AI Agent Isolation Into a One-Line Pod Spec
Red Hat detailed how OpenShift sandboxed containers give pods...
Hunt.io Catches an AI Agent Running Unsupervised in a Thai Finance Ministry Breach
Hunt.io found the open-source Hermes AI agent running unattended...
PromptArmor’s Connector Study Turns AI Agent Permissions Into a Moving Target
PromptArmor found more than a third of AI agent connectors...
Docker SBX Makes AI Agent Isolation a Runtime Boundary
Docker’s SBX and Sandbox Kits frame AI agent safety as a runtime...