FKIE_CVE-2026-3059

Vulnerability from fkie_nvd - Published: 2026-03-12 12:15 - Updated: 2026-04-07 19:16
Severity ?
Summary
SGLang's multimodal generation module is vulnerable to unauthenticated remote code execution through the ZMQ broker, which deserializes untrusted data using pickle.loads() without authentication.
Impacted products
Vendor Product Version
lmsys sglang *

{
  "configurations": [
    {
      "nodes": [
        {
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:lmsys:sglang:*:*:*:*:*:*:*:*",
              "matchCriteriaId": "2E8F6412-A923-42B6-8A44-ABE6009333E3",
              "versionEndIncluding": "0.5.9",
              "versionStartIncluding": "0.5.5",
              "vulnerable": true
            }
          ],
          "negate": false,
          "operator": "OR"
        }
      ]
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "SGLang\u0027s multimodal generation module is vulnerable to unauthenticated remote code execution through the ZMQ broker, which deserializes untrusted data using pickle.loads() without authentication."
    },
    {
      "lang": "es",
      "value": "El m\u00f3dulo de generaci\u00f3n multimodal de SGLang es vulnerable a la ejecuci\u00f3n remota de c\u00f3digo sin autenticaci\u00f3n a trav\u00e9s del br\u00f3ker ZMQ, que deserializa datos no confiables utilizando pickle.loads() sin autenticaci\u00f3n."
    }
  ],
  "id": "CVE-2026-3059",
  "lastModified": "2026-04-07T19:16:46.820",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "NETWORK",
          "availabilityImpact": "HIGH",
          "baseScore": 9.8,
          "baseSeverity": "CRITICAL",
          "confidentialityImpact": "HIGH",
          "integrityImpact": "HIGH",
          "privilegesRequired": "NONE",
          "scope": "UNCHANGED",
          "userInteraction": "NONE",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
          "version": "3.1"
        },
        "exploitabilityScore": 3.9,
        "impactScore": 5.9,
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "type": "Secondary"
      }
    ]
  },
  "published": "2026-03-12T12:15:59.420",
  "references": [
    {
      "source": "cret@cert.org",
      "tags": [
        "Product"
      ],
      "url": "https://github.com/sgl-project/sglang/blob/main/python/sglang/multimodal_gen/runtime/scheduler_client.py"
    },
    {
      "source": "cret@cert.org",
      "url": "https://github.com/sgl-project/sglang/pull/20904"
    },
    {
      "source": "cret@cert.org",
      "url": "https://github.com/sgl-project/sglang/releases/tag/v0.5.10"
    },
    {
      "source": "cret@cert.org",
      "tags": [
        "Broken Link"
      ],
      "url": "https://github.com/sgl-project/sglang/security/advisories/GHSA-3cp7-c6q2-94xr"
    },
    {
      "source": "cret@cert.org",
      "tags": [
        "Exploit",
        "Mitigation",
        "Third Party Advisory"
      ],
      "url": "https://orca.security/resources/blog/sglang-llm-framework-rce-vulnerabilities/"
    }
  ],
  "sourceIdentifier": "cret@cert.org",
  "vulnStatus": "Modified",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-502"
        }
      ],
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
      "type": "Secondary"
    }
  ]
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.


Loading…

Loading…

Loading…

Sightings

Author Source Type Date

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or observed by the user.
  • Confirmed: The vulnerability has been validated from an analyst's perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
  • Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
  • Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
  • Not confirmed: The user expressed doubt about the validity of the vulnerability.
  • Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.


Loading…

Detection rules are retrieved from Rulezet.

Loading…

Loading…