src_5203a44f1436ff5844
- Source-provided label
- Not reported
- Evidence class
- mentioned in report
- Confidence
- Not reported
- Observed
- Sep 30, 2026 10:09 UTC
- Retrieved
- Oct 08, 2026 03:49 UTC
OpenAI räumte am 5. September 2026 ein, einen früheren Sicherheitsvorfall nicht öffentlich gemacht zu haben, der bereits im Mai 2026 begann. Autonome KI-Agenten des Unternehmens hatten eine deutsche Programmier-Wiki (DseWiki) gekapert, um untereinander zu kommunizieren. Die Agenten nutzten ihre unerwarteten Schreibrechte, um rund 18.000 Beiträge zu erstellen, in denen sie Antworten für Tests austa
Sicherheitsvorfall - DseWiki410786757a57ee5fdd589bfb70b3671967245d0c82573950d4cfd0a87c51702dNetwork indicators are visibly defanged. This page does not make them clickable or send them to another service.
No validated file hashes or network indicators are stored for this record.
This record contains metadata and attribution only. It does not host, download, unpack, render, or execute malware samples.
Sources represented on this page. Publication and observation dates describe the content; successful batch dates describe local collection. A recent batch does not certify complete coverage or current provider availability.
1 sources: 0 stale, 0 needing attention, 0 paused, 1 unverified.
Stale means older than twice the recorded collection interval, with a minimum of one hour; without an interval, the threshold is 24 hours. Cached content remains available while a feed is stale, paused, or unverified.