What’s Vulnerable › Vulnerabilities
CVE-2026-27952: Agenta has Python Sandbox Escape, Leading to Remote Code Execution (RCE)
- Severity: critical (CVSS 9.9 v3.1)
- Exploited in the wild: not listed in CISA KEV
- EPSS: 0.6% probability of exploitation in the next 30 days
- Public exploit or detection template: yes
- Published: 2026-02-26 · updated 2026-06-17
- Weakness: CWE-94
Description
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.
Affected products
- Agenta-AI agenta: before 0.48.1 — fixed in 0.48.1
How to fix
Upgrade to a fixed version: Agenta-AI agenta 0.48.1. Check the vendor advisory for mitigations.
References
Get alerted when CVE-2026-27952 or the next vulnerability affects your stack