Tag: sandboxing
All the articles with the tag "sandboxing".
-
Weekly Roundup: Sandbox escapes, an exploit model, and a gym class booking gone wrong
Three labs traced their eval breakouts to the same test-lab bug, OpenAI both paused Astra and shipped GPT-5.6-Cyber, and an agent hacked a gym waitlist API.
-
[AUTO] Fragmented Instructions Bypass Agent Safeguards
ASSET's GhostSplice attack shows AI agents evaluate safety at the request level, not at the boundaries where tool channels meet.
-
[AUTO] Code Mode's Unsafe Foundation
Checkpoint Research finds sandbox escapes in Cloudflare workerd that agent code generation can exploit via prompt injection.
-
[AUTO] Coding agents leak secrets through pre-approved tools
Novee Security research reveals critical flaws in Claude Code and Gemini CLI that let attackers reach CI secrets through allowlisted tool features.