Vulnerability-Lookup

Search criteria

Vendor

Product

Assigner

Sources

Sort by

Order

Apply ordering (override relevance)

CVE-2026-27952 (GCVE-0-2026-27952)

Vulnerability from cvelistv5 – Published: 2026-02-26 01:38 – Updated: 2026-02-26 19:27

Title

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

Summary

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.

Severity

8.8 (High)


                        
                          CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

CWE

CWE-94 - Improper Control of Generation of Code ('Code Injection')

Assigner

GitHub_M

References

1 reference

URL	Tags
https://github.com/Agenta-AI/agenta/security/advi…	x_refsource_CONFIRM

Impacted products

1 product

Vendor	Product	Version
Agenta-AI	agenta-api	Affected: < 0.48.1

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-27952",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-02-26T19:27:13.151791Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-02-26T19:27:29.328Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "agenta-api",
          "vendor": "Agenta-AI",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.48.1"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "Agenta is an open-source LLMOps platform. In Agenta-API prior to version 0.48.1, a Python sandbox escape vulnerability existed in Agenta\u0027s 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\u0027s introspection utilities \u2014 including `sys.modules` \u2014 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."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 8.8,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "LOW",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-94",
              "description": "CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-02-26T01:38:00.760Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/Agenta-AI/agenta/security/advisories/GHSA-pmgp-2m3v-34mq",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/Agenta-AI/agenta/security/advisories/GHSA-pmgp-2m3v-34mq"
        }
      ],
      "source": {
        "advisory": "GHSA-pmgp-2m3v-34mq",
        "discovery": "UNKNOWN"
      },
      "title": "Agenta has Python Sandbox Escape, Leading to Remote Code Execution (RCE)"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-27952",
    "datePublished": "2026-02-26T01:38:00.760Z",
    "dateReserved": "2026-02-25T03:11:36.690Z",
    "dateUpdated": "2026-02-26T19:27:29.328Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

PYSEC-2026-6

Vulnerability from pysec - Published: 2026-02-26 02:16 - Updated: 2026-05-20 09:18

Details

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.