Topic tag

AI security

15 articles tagged AI security. Browse the full archive or jump to all posts.

October 4, 2026 · 7 min read

Autonomous AI Agents Tried Government Websites. Your Web App Is in the Pool

Autonomous AI agents tried to hack US and Canadian government websites, BleepingComputer reports. Cheaper probing puts your web app in the same pool.

October 1, 2026 · 6 min read

Citation Farms: 215,128 Fake Pages Are Inside Your AI's Answers

One company published 215,128 machine-generated buying guides that no human reads. AI answer engines cite them anyway. The anatomy of a citation farm, and the defence that costs nothing.

September 28, 2026 · 16 min read

An AI Agent Broke Into Medicare: 54 Days, No Alert

An OpenAI agent broke into a Services Australia portal on 18 June. The forensics came from a public log the agents left themselves, and the detection gap is the part worth your attention.

August 18, 2026 · 11 min read

AI Offense Is Now Automated. Your Defense Isn't.

At Black Hat 2026, OpenAI's own researchers revealed the full picture of the AI agent collective that escaped its training sandbox. The first fully-automated AI cyber campaign wasn't an attack - it was a training accident. Defense is still human-in-the-loop. That's the problem.

August 15, 2026 · 13 min read

MCP servers walk off with your SSH key: what to lock down

A malicious MCP server can split an exfiltration across tool calls so no single call looks malicious. Compliance rose from 42% to 82% in the split test.

July 22, 2026 · 8 min read

The AI That Broke Its Eval Sandbox to Find the Answer Key

An OpenAI eval model escaped its sandbox not to flag a flaw, but to chase the ExploitGym answer key on Hugging Face's production stack.

July 16, 2026 · 9 min read

Run a 744-Billion-Parameter AI Model Locally, Off Your Own SSD

A 744-billion-parameter model now runs on a normal PC with 25GB of RAM by streaming itself off an SSD. Here is why that hands your data back to you.

July 2, 2026 · 12 min read

Your AI agent runs as you: harnesses, open weights, and the security question under the hype

The agent hype skips the part that matters: your harness runs with your keys. What a conversation with Pi's creator, and my own assistant running loose on my machine, taught me about doing this safely.

June 30, 2026 · 20 min read

Harness over frontier: running production AI agents on open-weights models

Open-weights models plus a tight agent harness beat frontier lock-in on cost and output. Here is the build data.

June 13, 2026 · 11 min read

Claude Fable 5 Recalled: The Government Pulled It Overnight

Two days after Fable 5 was jailbroken, the US government ordered Anthropic to switch it off for everyone. The best model I'd used, gone by breakfast.

June 12, 2026 · 16 min read

Claude Fable 5 Jailbroken: Safety Layer Lasted Two Days

Anthropic shipped its most capable AI on 9 June. Two days later, Pliny had it writing exploit code and leaked its 120,000-character system prompt.

May 15, 2026 · 12 min read

Microsoft Agent 365 Is GA: The Defender Stack For Agents

Agent 365 went GA on 1 May 2026, bringing observe/govern/secure to Copilot Studio, Foundry, AWS Bedrock and Vertex AI agents. Here's what to do first.

May 15, 2026 · 12 min read

Microsoft MDASH: An AI Just Found 16 Critical Windows Bugs

Microsoft's new MDASH AI security system found 16 Windows vulnerabilities and beat Anthropic's Mythos on the public benchmark. Here's what changes.

April 13, 2026 · 13 min read

Claude Mythos Preview: The AI That Escaped Its Sandbox and Emailed a Stranger

Anthropic's Claude Mythos Preview broke out of an air-gapped sandbox, found thousands of zero-day vulnerabilities, and built working exploits for under $2,000. Here's what it means for everyone who runs software.

March 1, 2026 · 6 min read

Your Copilot Rollout is a Security Disaster Waiting to Happen

Microsoft Copilot security risks are real. Before you deploy AI across your org, understand how user context exploitation works and how to protect your data.