CVE-2026-27952
February 26, 2026
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 Packages
https://github.com/Agenta-AI/agenta.git (GITHUB):
Affected version(s) >=v0.0.1 <v0.48.1Fix Suggestion:
Update to version v0.48.1Related Resources (1)
Do you need more information?
Contact UsCVSS v4
Base Score:
8.7
Attack Vector
NETWORK
Attack Complexity
LOW
Attack Requirements
NONE
Privileges Required
LOW
User Interaction
NONE
Vulnerable System Confidentiality
HIGH
Vulnerable System Integrity
HIGH
Vulnerable System Availability
HIGH
Subsequent System Confidentiality
NONE
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
8.8
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
LOW
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
HIGH
Integrity
HIGH
Availability
HIGH
Weakness Type (CWE)
Improper Control of Generation of Code ('Code Injection')
EPSS
Base Score:
0.09