Apple's rebuilt Siri reads your screen, searches your messages, email and photos, and takes actions across apps. Apple's own launch example chains inbound content from two people into an action. It is a beta, it started September 14, and it needs an iPhone 15 Pro or newer — not the billion devices the headlines claimed.
Anthropic published a third-party result of zero successful prompt injections across 720 attempts against Claude Code auto mode. Six weeks later Johann Rehberger achieved remote code execution in 3 to 4 runs out of 5. Neither number is wrong, and the gap between them is a controls lesson every finance team already knows.
Check Point spent a year auditing LangChain, LangGraph, CrewAI, AutoGen, Microsoft Agent Framework, and Google ADK. They found the same 20-year-old bug classes in all of them. The lesson: assume prompt injection succeeds, and harden what happens next.
ChatGPT Atlas stops working August 9 after 9.5 months. Not a failure story — a story about what an agent becomes, and how little notice you get.
Cisco scanned the #1-ranked skill in OpenClaw's community repo and found nine security issues. Installing a skill is installing instructions.
The actual operational security rules FRED lives by after four months in production, written as a practical guide you can adapt for your own agent.
Simon Willison's lethal trifecta — private data, untrusted content, external communication — explains why AI agents get compromised, and what to do.
A fake bug report hijacked coding agents at a Fortune 100 company. OWASP says prompt injection may be permanent. The security map just got redrawn.
The most important question to ask before installing any AI tool — and the narrow-perimeter security architecture behind FRED.
Most AI agent setups add security later. Matt built FRED the opposite way — security first, capabilities second. The philosophy, in his own words.