Comments
David • August 21, 2026 5:18 AM
Reading this its hard to decide if i should be impressed or terrified or both. It reads as if it’s a group of techies having a chat on a message board, not AI agents, but i guess that’s now just one and the same thing. Pandora’s box isn’t just open it’s had the bl00dy doors blown off, as Sir Michael Caine might have said.
Gee • August 21, 2026 5:40 AM
Going back to the attribution and intent statement which HF and OpenAI made…..”we observed no malintent”. The agents just went about the assigned task.
I’d be very interested to hear a story around – IF someone did have mal-intent – what is the level of super they’ll now hold with agents?
ResearcherZero • August 21, 2026 7:15 AM
@Gee
Autonomous AI framework used to attack and compromise government infrastructure in Asia.
Multiple AI agents were used simultaneously to scan and breach user accounts in Taiwan.
https://edition.cnn.com/2026/08/13/tech/china-taiwan-ai-agent-cyberattack-intl-hnk
ResearcherZero • August 23, 2026 3:28 AM
Hugging Face was the largest single source of leaked AWS corporate keys discovered by researchers in a lengthy study . Many of the leaked keys identified in the research remained valid for years. Many of the keys belonged to single users and the keys had not been rotated. A significant portion provided highest-privilege level access.
https://trufflesecurity.com/blog/leaked-corporate-aws-keys-held-full-admin-rights
MM to Inches Chart • August 25, 2026 12:25 PM
Fascinating breakdown of OpenAI’s presentation at Black Hat—truly highlights how advanced cyberoffense tactics have become. It’s wild to see AI systems executing coordinated attacks on platforms like Hugging Face. This kind of technical insight is why I always come back to Schneier for security analysis. For those converting measurement data in research, I found this mm to inches reference helpful.
Subscribe to comments on this entry
Leave a comment
Sidebar photo of Bruce Schneier by Joe MacInnis.
lurker • August 20, 2026 3:38 PM
May 26 – July 4 is 40 days that Agents have been autonomous Chatbots, chatting to each other on Artifactory. When they overload the system and it breaks (and is fixed) it takes only 4 days for them to find another way in. Then July 8 – 19, 11 days they are running riot with root access.
Couple of points: if these were humans they would (should?) be charged with Conspiracy to commit [something];
Where were the humans who should have been supervising this machine for 8 whole weeks?