Agenta has Python Sandbox Escape, Leading to Remote Code Execution (RCE)
Agenta is an open-source LLMOps platform. In Agenta-API prior to version 0.48.1, a Python sandbox escape vulnerability existed in Agenta's custom code evaluator. Agenta used RestrictedPython as a sandboxing mechanism for user-supplied evaluator code, but incorrectly whitelisted the `numpy` package as safe within the sandbox. This allowed authenticated users to bypass the sandbox and achieve arbitrary code execution on the API server. The escape path was through `numpy.ma.core.inspect`, which exposes Python's introspection utilities — including `sys.modules` — thereby providing access to unfiltered system-level functionality like `os.system`. This vulnerability affects the Agenta self-hosted platform (API server), not the SDK when used as a standalone Python library. The custom code evaluator runs server-side within the API process. The issue is fixed in v0.48.1 by removing `numpy` from the sandbox allowlist. In later versions (v0.60+), the RestrictedPython sandbox was removed entirely and replaced with a different execution model.
Problem Types
| Type | CWE ID | Description |
|---|
| CWE | CWE-94 | CWE-94: Improper Control of Generation of Code ('Code Injection') |
Type: CWE
Description: CWE-94: Improper Control of Generation of Code ('Code Injection')
Metrics
| Version | Base score | Base severity | Vector |
|---|
| 3.1 | 8.8 | HIGH | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H |
Version: 3.1
Base score: 8.8
Base severity: HIGH
Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H