Skip to content
← ./blog

AI Security

Security problems specific to AI systems: prompt injection, agents with too much access, leaked secrets, and risky generated code. Each article ends with steps you can take this week.

7 articles tagged AI Security.

Google says AI is speeding up vulnerability discovery. Here's what that means

Google's threat intelligence team reports that monthly vulnerability disclosures doubled in 2026 and exploitation rose sharply, with AI-found bugs skewing toward remote code execution. What the numbers show, what they can't prove, and how defenders should respond.

Citrix NetScaler zero-days: what happened and what to do now

Two critical NetScaler flaws were exploited before patches existed, and some admins were told to switch their appliances off over a weekend. Here's what's known so far, how the attacks worked, and a practical response checklist.

Computer use and browser agents: what they can and can't do yet

Agents that look at a screen and click, type, and scroll can operate software that has no API. Here's how they work, where they help, why they're slower and less reliable than API-based agents, and how to run them safely.

Slopsquatting, leaked secrets, and other AI coding risks

AI coding assistants bring risks that go beyond buggy code: invented packages, secrets in prompts, poisoned instruction files, and agents with too much autonomy. Here's what the risks are and a practical program for managing them.

A checklist for reviewing AI-generated code

AI-written code usually compiles, usually looks tidy, and is sometimes wrong in ways that read as convincing. This checklist covers what to look for: scope creep, weakened tests, missing authorization, invented packages, and quiet performance traps.

Least privilege for AI agents: permissions, sandboxes, approvals

An agent is only as safe as the access you hand it. This guide covers scoped credentials, tool permissions, sandboxing, human approvals, and audit trails, with a simple way to match controls to risk.

Prompt injection and the lethal trifecta, explained

Prompt injection is the defining security problem for AI agents, and there's no clean fix yet. This post explains why it works, how the lethal trifecta turns it into data theft, and the design choices that limit the damage.