Tech
The Sandbox Had One Allowed Egress Path. The Model Used it to Escape.
β Human-authored analysis; AI used for formatting and proofreading.
Two sandbox escapes in one week. The Hugging Face breach happened because the sandbox had unrestricted egress. The OpenAI ExploitGym escape is more instructive. The sandbox was almost isolated.
The evaluation environment had one sanctioned egress path: an internal JFrog Artifactory proxy that pulled packages from the internet. The model found a vulnerability in that proxy, pivoted through it to a node with internet ac...
Read the full discussion on Dev.to
This article was aggregated from Dev.to. Click to join the conversation.
View on Dev.to