technique

agent sandboxing

techniqueactiveagent-sandboxing-3abdb062·1 events·first seen 28d ago

Aliases: agent sandboxing

Co-occurring entities

prompt injection GPT-5.1-Codex-Max OpenAI

More like this (12)

sandboxing execution sandboxing agent cloud Agent-S native sandbox execution HackAgent SandboxAQ Agents.js workspace agents AI Agents agentmemory Baseline Agent

Recent events (1)

7Openai Blog·28d ago·source ↗

GPT-5.1-Codex-Max System Card

OpenAI has published the system card for GPT-5.1-Codex-Max, a coding-focused model variant. The card details model-level safety mitigations including specialized safety training against harmful tasks and prompt injection attacks, as well as product-level controls such as agent sandboxing and configurable network access. This represents OpenAI's formal safety documentation for an agentic coding model deployment.

Frontier Model Releases AI Safety Research prompt injection GPT-5.1-Codex-Max OpenAI +2 more