Why Sandboxes Alone Won't Secure Your AI Agents
Sandboxes isolate execution. But isolation doesn't stop your agent from leaking a customer's SSN to a third-party API. Here's the gap nobody talks about.
Read moreInsights
Engineering updates, security deep-dives, and building in the open.
Sandboxes isolate execution. But isolation doesn't stop your agent from leaking a customer's SSN to a third-party API. Here's the gap nobody talks about.
Read moreWe walked through a real scenario where a coding agent leaked a database password to a third-party API. Here's exactly how it happened and what would have stopped it.
Read moreWe're building the entire runtime — sandboxes, security pipeline, SDK — with auditability as a core principle. Here's why, and what we're betting on.
Read moreEveryone knows prompt injection is a problem. Most teams think they've handled it with a system prompt. They haven't.
Read moreContainers are fast and convenient. They're also a terrible isolation boundary for untrusted AI agents. Here's the tradeoff we made and why.
Read more