* Pure execution-allowlist guard. Decides whether a candidate execution environment is permitted to run an agent, given the instance-level execution policy. This is security-critical: on a shared cloud instance we FORCE all untrusted tenant agents onto the Kubernetes sandbox-prov
// Source: https://github.com/paperclipai/paperclip | License: MIT | Copyright 2025 Paperclip AI
// Provided via justclaw.it.com; keep this notice with the code.
/**
* Pure execution-allowlist guard.
*
* Decides whether a candidate execution environment is permitted to run an
* agent, given the instance-level execution policy. This is security-critical:
* on a shared cloud instance we FORCE all untrusted tenant agents onto the
* Kubernetes sandbox-provider and REFUSE local/in-process execution so that a
* tenant agent can never run inside the server process or on an unsandboxed
* local/ssh adapter.
*
* The merged tree's environment model represents the Kubernetes sandbox as a
* core `driver: "sandbox"` environment whose `config.provider` is the plugin's
* `driverKey` ("kubernet
... (truncated -- full source via MCP)
See the full source, get the GitHub permalink, and search for more like it.
Get a free API key