Topics / agent security risk

Attributed viewpoint

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.

Behind the viewpoint

Translations are for reading; original excerpts remain the evidence.

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

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.
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..