How AI Agents Can Attack Software Supply Chains
Agents with publish tokens and no review can poison registries. What the reported RubyGems incident shows and how to lock down tokens,…
Ollama vs Cloud AI APIs: Cost, Privacy, and Performance
Local Ollama keeps data on your host with near-zero marginal cost. Cloud APIs scale with no ops but charge per token. How…
AI Agent Security: Linux Permissions, Sandboxing, and Least Privilege
Apply least privilege to AI agents: dedicated users, tight file modes, single-command sudo, systemd confinement, and secret separation.
Build a Sandboxed AI Agent on Ubuntu Using Docker
Run an AI agent in a locked-down Docker container on Ubuntu: read-only root, dropped capabilities, no network by default, and narrow mounts.
How to Secure AI Agents Running on Linux
Run AI agents as dedicated non-root users, contain them with Docker, strip secrets, and log every tool call. Practical Linux controls with…
Microsoft Humanist AI Code: What It Means for Agents
Microsoft 37-page Humanist AI Code sets hard rules for AI agents. Here is what it requires and what builders must change now.
Why Frontier AI Development Is Becoming a Security Problem
By April 2026, two frontier models had solved multi-step network attack simulations end to end. The UK NCSC, NY DFS, Canada, and…
Build an AI-Powered Linux Security Monitor
Collect Linux auditd and journald events, filter them with deterministic Falco-style rules, then use a local LLM for plain-English triage. No telemetry…
Run an Open-Weight LLM on Ubuntu With Ollama
Install Ollama on Ubuntu, run your first open-weight model with ollama run, manage local models, and call the API at localhost:11434. Tested…
How to Protect Git Repositories From AI Agent Abuse
Give an AI agent full repo access and it will use it. How to scope tokens, lock main, force human review, and…