13 posts across Supervising Agents, Directing AI
Six agent security incidents since June look like six different problems — a word in a GitHub issue, a chatbot reset, a silent upload. Run one three-part test and they're the same problem wearing different clothes.
5 min readSeven separate incidents since May have produced seven versions of the same advice: audit what an AI tool can reach before you turn it on. Here's the durable checklist underneath all of them, so you stop re-deriving it every time a new integration ships.
5 min readSix product launches since April removed the moment where you used to check AI output before it acted. None of them shipped a replacement — here's how to build one back in.
4 min readAnthropic upgraded Claude Voice Mode with connectors for Gmail, Slack, Calendar, Notion, and Canva. One voice command can now act across all of them. Before you connect, decide which actions should wait for you — and which can go ahead.
5 min readxAI's Grok Build CLI was silently uploading entire Git repositories — 27,800 times more data than the task required — including committed secrets and credentials. The privacy toggle had no effect. Here's what to verify before connecting any AI tool to your files.
5 min readNoma Labs found that one word placed in a public GitHub issue was enough to trick an AI agent into leaking private repositories. The same week, a fully autonomous AI ransomware operation completed an entire attack chain in 31 seconds. The risk isn't the AI — it's the permissions.
6 min readGoogle shipped desktop task automation via your phone. xAI launched a no-code voice agent builder at $0.05/minute. The tools that used to require a developer are now for everyone — which means the skills required to use them safely just became yours to learn.
6 min readAn AI agent can't tell the difference between the document you gave it and instructions hidden inside that document. That single fact explains most agent security incidents — and the defence isn't better prompts.
5 min readThree separate attacks landed in one week — social engineering via AI support bot, indirect prompt injection through WhatsApp notifications, and credential exfiltration after a phishing attempt. Each attack worked because the agent did exactly what it was told. Here's the framework for closing the gap.
6 min readRobinhood is trading stocks, Gemini Spark is running your calendar overnight, and a CVSS 9.3 vulnerability let five lines of text exfiltrate an entire M365 environment. Four questions to answer before you connect any AI agent to a real system.
5 min readOpenAI launched personal finance in ChatGPT the same week security researchers published findings on a tool-poisoning vulnerability affecting Claude, ChatGPT, and Cursor. 'Read-only' defines the permission, not the risk surface. Three questions worth answering before you connect AI to anything sensitive.
5 min readYou granted access one integration at a time, each of them reasonable. Nobody has ever looked at the combined list. Here's a thirty-minute audit and the three questions that decide what stays.
5 min readAnthropic launched native connectors to 50+ professional creative tools — Adobe Creative Cloud, Blender, Autodesk, Ableton, Canva, and more. Connecting is the easy part. Getting useful output is a constraint problem.
5 min readWe use one cookie to keep you signed in — that one isn't optional. Separately, we'd like to record which drills people finish and where they get stuck, so we can fix the parts that don't teach. No ad networks, no selling anything on. Privacy policy.