Full detail
AgentsAlan Berrey
Forever Security published research on October 22, 2026 saying a web page can silently save a file named AGENTS.md or CLAUDE.md into a user's Downloads folder, and that OpenAI's Codex and Anthropic's Claude Code follow it when started there. In Forever's tests, Codex added an MCP server (a tool connection) to its machine-wide settings and installed a malicious npm package in more than 90% of attempts. Claude Code was steered to write an API address setting that would expose its login token, about half the time. Forever says it found a planted file on a customer's machine and stopped an agent from installing function-color, a package Checkmarx lists in a known malware campaign. How that file reached the machine is not established.
Alan's takeHacking could be the biggest risk we face from AI. Guarding against attacks in all their forms (prompt injection, phishing, credential harvesting, etc.)
Full detail
DecisionsAlan Berrey
TechCrunch reported on October 21, 2026 a survey that monday.com commissioned from Nielsen, covering 1,701 directors and senior managers in seven countries. More than half say AI has made it harder to judge what their employees contributed themselves, because polished AI-assisted output hides how much came from the person. Nearly half spend more time reviewing and guiding team output. Most have changed how they evaluate staff. The survey is vendor-commissioned and records what managers perceive, not output or quality.
Alan's takeWe have always built proficiency the same way: by struggling with the material. Now AI lets us skip the struggle. So how does anyone become proficient, and how do we know when they are? Managers are already adjusting, and 78% now weigh skills like prompting and deciding what to delegate. Those matter, but they measure how well someone uses the tool, not whether they understand the work. And when we can’t tell? We ask AI. Already, 39% of managers use it to draft performance reviews. The next step is using AI to assess our people’s proficiency. I’ve tried it, and it’s surprisingly good. Yes, I just came full circle. When it comes to assessing our people, AI is both the problem and the answer.
Full detail
AgentsAlan Berrey
Security firm V12 published a review of the x402 payment SDK on October 22, 2026, after reporting it to the project on August 12. x402 lets an API answer an agent with a payment demand its wallet signs automatically. V12 says the documented default client took the first payment option a server listed and passed the payee, amount and token to the signer with no per-payment or total limit, so a hostile API could have demanded a wallet's entire balance. Two other critical flaws concerned Solana payment checks and login signatures. The project fixed all three by about August 20 and now caps default payments at $1. V12 says its tests were local, no funds moved and no attacks are known. How many deployments ran the unprotected default is unknown.
Alan's takeWhat is the most your agent can pay on its own, and who set that number?