Managing the cyber risk of agentic AI
- Published
- Record updated
Summary
This regulatory guidance advises that AI agents always run within a sandboxed environment that controls what resources they can reach locally and over a network. It recommends defining the sandbox boundaries across execution, network, compute, credentials and data, and denying network traffic by default, using allowlists or protocol-aware proxies with manual approval. It also warns that agents may discover and exploit configuration issues or vulnerabilities in technical controls, leading to a sandbox escape, so it calls for multiple isolation layers and regular validation.
Mitigation
Run AI agents within a sandboxed environment that controls and manages what resources can and cannot be communicated with, both locally and over a network. Deny all inbound and outbound network traffic by default and allow only required connections using allowlists, or use protocol- or service-aware proxies that permit connections by exception with manual approval. Restrict each agent to the minimum resources its task needs, use multiple layers of isolation, choose mature sandbox technologies, and regularly validate configurations.