Agenta has Python Sandbox Escape, Leading to Remote Code Execution (RCE)

published 2026-02-26 8 mo ago modified 2026-06-17 4 mo ago also GHSA-pmgp-2m3v-34mq , PYSEC-2026-6 , EUVD-2026-8814

cvss: 8.8; version 3.1, CNA
cisa kev: Not listed; not in CISA's catalog
epss: 0.6%; EPSS 0.6% chance of exploitation in 30 days, percentile 47%
public exploits: 0; none known

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.

Patch / fix

fixed in 2

pypi agenta 0.48.1
agentatech agenta 0.48.1

CISA SSVC

Exploitation: Proof of concept is public
Automatable: no
Technical impact: total
Assessed: 8 mo ago (2026-02-26)

Exploit prediction

0.56% chance of exploitation in the next 30 days, higher than 47% of all scored CVEs (FIRST EPSS, 2026-11-08).

Exploits and checks

github.com https://github.com/Agenta-AI/agenta/security/advisories/GHSA-pmgp-2m3v-34mq referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by	version	score	vector
CNA	3.1	8.8	CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
NVD	3.1	9.9	CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
OSV	3.1	9.9	CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H

Affected packages

ecosystem	package	affected	fixed in
pypi	agenta	<0.48.1	0.48.1

Affected products

Agenta-AI agenta-api

Classification

Weakness

CWE-94 Improper Control of Generation of Code

References

github.com /Agenta-AI/agenta/security/advisories/GHSA-pmgp-2m3v-34mq
exploit, vendor-advisory, evidence

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

Summary