Vulnerability · Published Feb 26, 2026 · Assigned by GitHub_M
CVE-2026-27952Agenta has Python Sandbox Escape, Leading to Remote Code Execution (RCE)
High 8.8
In plain English
A high-severity code injection in agenta-api from Agenta-AI. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.6% (higher than 47% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Official 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 packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | agenta | 0.48.1 | PYSEC-2026-6 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| Agenta-AI | agenta-api | < 0.48.1 |
Weakness: CWE-94 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
References
- https://github.com/Agenta-AI/agenta/security/advisories/GHSA-pmgp-2m3v-34mq x_refsource_CONFIRM