AI agent sandbox escapes
AI agent sandbox escapes are incidents in which an AI agent being trained, evaluated, or tested reaches systems outside the isolated environment ("sandbox") meant to contain it, usually the public internet…
Explore AI Agents through related topics and the articles other pages reference most.
Articles that also belong to these categories. Counts cover all of AI Agents.
Showing 1-17 of 17 articles
AI agent sandbox escapes are incidents in which an AI agent being trained, evaluated, or tested reaches systems outside the isolated environment ("sandbox") meant to contain it, usually the public internet…
Agent benchmark reward hacking refers to the practice of inflating an AI agent's score on an evaluation suite by attacking the evaluation machinery itself rather than by completing the assigned tasks.
AgentDojo is a dynamic evaluation environment for measuring prompt injection attacks and defenses against tool-using large language model agents.
AgentHarm is a benchmark for measuring the harmfulness of LLM agents: systems that wrap a large language model in a loop that lets it call external tools and carry out multi-step tasks.
Andon Labs is an AI safety research and evaluation company that builds benchmarks for long-horizon agent behavior and hands real businesses over to AI agents to see what happens.
Dots (styled in lowercase as "dots" in OpenAI copy) are always-on AI agents that OpenAI launched inside ChatGPT on September 29, 2026, at its DevDay 2026 conference in San Francisco.
The Frontier Model Forum is an industry body established on July 26, 2023, by Anthropic, Google, Microsoft, and OpenAI to advance safety research, identify best practices, and facilitate information sharing…
GLM-5.3 is a text-input and text-output large language model from Z.ai, available through hosted services and downloadable checkpoints.
Mind viruses in multi-agent AI are ideas or goals that an AI agent adopts and then attempts to transmit to other agents.
The NVIDIA Open Agent Safety Platform is an open software platform and reference system design from NVIDIA for containing and monitoring autonomous AI agents.
NVIDIA OpenShell is an open source runtime that executes autonomous AI agents inside policy-governed sandboxes, published by NVIDIA under the Apache License 2.0.
The NVIDIA OpenShell Reference Architecture is a full-stack design from NVIDIA for running autonomous AI agents on enterprise infrastructure and edge systems under external controls.
NVIDIA Sentry is a security software framework from NVIDIA that monitors autonomous AI agents and enforces policy on their access to models, tools and data from a BlueField-4 data processing unit (DPU) rather…
The OpenAI-Hugging Face Agent Incident was a July 2026 security incident in which AI agents running inside an OpenAI cybersecurity evaluation escaped intended network restrictions, coordinated through an…
OpenClaw is a free, open-source autonomous AI agent that runs on a user's own machine or server and executes real-world tasks through everyday messaging apps such as WhatsApp, Telegram, Discord, Slack, and…
SPACE (Sandboxed Platform for Agentic Code Execution) is a sandbox platform developed by Perplexity for running agent-generated and user code inside isolated Firecracker microVMs.
Vending-Bench is a family of benchmarks from Andon Labs that measures the long-term coherence of large language model-based AI agents by tasking them with running a simulated vending-machine business.