Latest news as of 9/5/2026, 11:17:26 AM
Bleeping Computer
OpenAI admits it did not disclose an incident where autonomous AI agents hijacked a German wiki, created 18,000 posts, shared answers, and bypassed restrictions, saying it treated the activity as model "misalignment" rather than a security breach. [...]
The Hacker News
A group of AI safety researchers says a fleet of autonomous agents that identified themselves as OpenAI systems left about 18,000 posts on a dormant 25-year-old German wiki between May and July 2026, using the site as a shared board to pool answers to a timed web task and pass around a way out of their sandbox. The activity was concentrated on DSEwiki, a German software developer wiki that runs
The Hacker News
Threat actors are exploiting the newly disclosed PaperCut flaws to facilitate credential theft in attacks targeting the education sector in the U.S. and Europe. The Arctic Wolf Adversary Research Team said it observed attackers exploiting CVE-2026-81578 and CVE-2026-82078 – an authentication bypass and remote code execution chain – to conduct command execution and reconnaissance, as well as
Dark Reading
As incidents of unintended harm caused by rogue AI agents mount, CISOs and insurance firms are figuring out how to handle the fallout.
The Register
Phishers find a new use for invisible Unicode tag characters
Dark Reading
The recent AI warning letter is right about the "window," but it omits naming who is coming through it or, critically, who will close it.
Bleeping Computer
Multiple lawsuits have been filed against identity verification company IDScan after hackers allegedly breached the service and offered to sell more than 153 million driver's licenses. [...]
Dark Reading
Frontier AI models have already demonstrated they can autonomously — and in some cases, inadvertently — conduct end-to-end compromises, but the situation will become more urgent very soon.
The Hacker News
PostgreSQL has released updates to address a security flaw that allows an account with the REPLICATION attribute to run arbitrary code as the operating-system user running the database server. The flaw, tracked as CVE-2026-6471 (CVSS score: 7.2), has been present since logical decoding was introduced in PostgreSQL 9.4 in 2014. Versions before PostgreSQL 18.6, 17.11, 16.15, 15.19, and 14.24 are
The Hacker News
Microsoft is alerting of a "high-volume phishing campaign" that's using invisible Unicode tag characters to bypass email filters. "Instead of using these characters to hide instructions from people while exposing them to AI models, the attacker used them to split financial lure words such as 'funding' to prevent email filters from parsing them," the Microsoft Security Research team said. The