Sidecars: A low-latency trust boundary for Sandboxes | Modal Blog

Synthesis

1. 01

   Existing isolation uses an outdated unit of trust

   Johnston says technologies such as gVisor and Firecracker isolate the platform from users and users from one another. She calls that unit of trust outdated and asks how to protect users from their “own” code.

   Supporting evidence 1

   Original excerpt

   technologies like gVisor and Firecracker “solved” “isolation” nearly eight years ago. Unfortunately for us, they solved it for an now-outdated unit of trust. How do you protect users from their “own” code?

   Olivia Johnston · Paragraph 1

   Sidecars: A low-latency trust boundary for Sandboxes | Modal Blog · Oct 1, 2026

   Context

   At Modal, our customers rely on Sandboxes to execute untrusted code written by their downstream users or, almost exclusively now, by agents. Running untrusted code isn’t a new problem: every cloud provider has to do this from day 1 to isolate their platform from their user and their users from each other. Fortunately,

   Read in source context →

   Continue exploring

   trust boundary design →
2. 02

   Sidecars provide 3x faster cross-boundary communication in the stated comparison

   Johnston describes Sidecars as isolated containers that run alongside a main Sandbox on the same host. She reports 3x faster communication across trust boundaries than using separate Sandboxes, particularly for operation-heavy workloads.

   Supporting evidence 1

   Original excerpt

   Sidecars enable 3x faster communication across trust boundaries than using separate Sandboxes — which is particularly helpful for operation-heavy workloads.

   Olivia Johnston · Paragraph 2

   Sidecars: A low-latency trust boundary for Sandboxes | Modal Blog · Oct 1, 2026

   Context

   Today we’re excited to introduce Sidecars, which are our broader answer to this problem. Sidecars are isolated containers that run alongside your main Sandbox on the same host and provide a real security boundary between trusted or untrusted code.

   Read in source context →

   Continue exploring

   performance-security tradeoff →
3. 03

   Agent harness in same Sandbox creates lethal trifecta

   Johnston cites Simon Willison’s “lethal trifecta”: access to private data, exposure to untrusted content and the ability to communicate externally can allow a tricked agent to leak data. She says a coding agent whose harness runs in its Sandbox has all three by default.

   Supporting evidence 1

   Original excerpt

   Simon Willison calls it the lethal trifecta : an agent with access to private data, exposure to untrusted content, and the ability to communicate externally can be tricked into leaking that data. A coding agent whose harness runs in its Sandbox has all three by default.

   Olivia Johnston · Paragraph 8

   Sidecars: A low-latency trust boundary for Sandboxes | Modal Blog · Oct 1, 2026

   Context

   Hosting the harness and the tool calls together is a security risk. The harness's credentials sit next to generated code, the agent can read untrusted content from the web, like packages and repos, and anything in the Sandbox can make network calls..

   Read in source context →

   Continue exploring

   agent security risk →