Together.ai: Prompt Leakage for Requests
Fe2O3
13 points
6 comments
November 22, 2026
Related Discussions
Found 5 related stories in 352.6ms across 13,334 title embeddings via pgvector HNSW
- Google: Attackers are using prompt injection against coding agents fourfire · 11 pts · September 09, 2026 · 61% similar
- Leaky AI supply chain is exposing secret user data at an alarming rate BoiledCabbage · 15 pts · November 20, 2026 · 56% similar
- Security incident disclosure – July 2026 fdb · 24 pts · July 19, 2026 · 55% similar
- Detecting and countering misuse of AI: September 2026 garo-pro · 110 pts · September 10, 2026 · 54% similar
- A Privacy Analysis of Web and Mobile Conversational AI Agents [pdf] damaru2 · 414 pts · September 29, 2026 · 53% similar
Discussion Highlights (4 comments)
nickandbro
The mass hacking continues…
sans_souse
Am I inferring correctly here, in that Dragos basically had some sort of experiment set up and running for exactly this scenario, that effectively allowed them to trace the breach to the individual?
tczMUFlmoNk
> During development of our public GitHub repository, xorl, an AI coding agent committed a credential that provided access to the private Hugging Face repository My emphasis on the accountability laundering. No, "xorl" did not do this— you did. And, if "xorl" is https://github.com/togethercomputer/xorl and `togethercomputer` is together.ai, then you wrote "xorl" and are doubly responsible. If five years ago I had said, "During development of our public GitHub repository, my computer decided to commit a credential", this would have been immediately recognized for the embarrassing abdication of duty that it is. So, too, should this be now.
alwa
…I was wondering why Claude started recommending a layer of high-perplexity canary tokens for a document-watermarking project I was working on…