Leaky AI supply chain is exposing secret user data at an alarming rate
BoiledCabbage
15 points
3 comments
November 20, 2026
Related Discussions
Found 5 related stories in 305.2ms across 13,334 title embeddings via pgvector HNSW
- AI models keep posting screenshots showing sensitive data from inside companies Dotnaught · 20 pts · September 29, 2026 · 69% similar
- Terabytes of credentials leaked in supply-chain attack RattlesnakeJake · 42 pts · August 13, 2026 · 67% similar
- OpenAI discloses four more rogue incidents DASD · 123 pts · October 17, 2026 · 64% similar
- A Defense Contractor Gave Their AI Agent Access to a Secure Pentagon System cdrnsf · 19 pts · October 29, 2026 · 64% similar
- OpenAI and Anthropic oversold AI security breaches hei-lima · 34 pts · September 19, 2026 · 62% similar
Discussion Highlights (3 comments)
jrmg
Each key was sent in exactly one request to one provider, all within a few short windows in late October, and every request we sent during those windows was stolen. Some of the stolen keys came from requests that the provider rejected before a model ever ran—this tells us that the attacker was copying requests at the provider’s front door, and not somewhere deeper in the inference stack. In the other two breaches, some of the stolen requests were marked as ZDR. A privacy flag doesn’t help when the attacker is already inside. This seems too incredible to be true. Every key being sent through these routers was stolen and reused? And no one has noticed this until now?
frizkie
Am I missing something here? Surprised this doesn't have more comments (of any form). Neither do the other reports of the same investigation from other outlets.
jrmg
Related? https://news.ycombinator.com/item?id=50585962