{
  "affected": [
    {
      "affectedData": [
        {
          "product": "vllm",
          "vendor": "vllm-project",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.22.0"
            }
          ]
        }
      ],
      "source": "security-advisories@github.com"
    }
  ],
  "configurations": [
    {
      "nodes": [
        {
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
              "matchCriteriaId": "981922E2-F268-4829-9CDE-3A165F3808B9",
              "versionEndExcluding": "0.22.0",
              "vulnerable": true
            }
          ],
          "negate": false,
          "operator": "OR"
        }
      ]
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, an assert-based security check in vLLM\u0027s activation function loading allows any unauthenticated attacker to achieve arbitrary code execution on the server by publishing a malicious HuggingFace model, when vLLM runs in Python optimized mode (python -O or PYTHONOPTIMIZE=1). This vulnerability is fixed in 0.22.0."
    }
  ],
  "id": "CVE-2026-41523",
  "lastModified": "2026-06-24T16:48:45.290",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "HIGH",
          "attackVector": "NETWORK",
          "availabilityImpact": "HIGH",
          "baseScore": 7.5,
          "baseSeverity": "HIGH",
          "confidentialityImpact": "HIGH",
          "integrityImpact": "HIGH",
          "privilegesRequired": "NONE",
          "scope": "UNCHANGED",
          "userInteraction": "REQUIRED",
          "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H",
          "version": "3.1"
        },
        "exploitabilityScore": 1.6,
        "impactScore": 5.9,
        "source": "security-advisories@github.com",
        "type": "Secondary"
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-41523",
          "options": [
            {
              "exploitation": "none"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "role": "CISA Coordinator",
          "timestamp": "2026-06-23T12:23:15.308986Z",
          "version": "2.0.3"
        }
      }
    ]
  },
  "published": "2026-06-22T23:16:30.200",
  "references": [
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Patch"
      ],
      "url": "https://github.com/vllm-project/vllm/commit/b3c7ffcab82c2439726f8cb213800f6f38c023d3"
    },
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Exploit",
        "Third Party Advisory"
      ],
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-q8gq-377p-jq3r"
    },
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Third Party Advisory"
      ],
      "url": "https://huntr.com/bounties/dcb05b04-e625-41e7-adbc-bbae0cc2d64c"
    }
  ],
  "sourceIdentifier": "security-advisories@github.com",
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-94"
        },
        {
          "lang": "en",
          "value": "CWE-617"
        }
      ],
      "source": "security-advisories@github.com",
      "type": "Secondary"
    }
  ]
}

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "vllm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.22.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-41523"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-617",
      "CWE-94"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-06-16T17:34:49Z",
    "nvd_published_at": null,
    "severity": "HIGH"
  },
  "details": "### Summary\n\nAn `assert`-based security check in vLLM\u0027s activation function loading allows any unauthenticated attacker to achieve arbitrary code execution on the server by publishing a malicious HuggingFace model, when vLLM runs in Python optimized mode (`python -O` or `PYTHONOPTIMIZE=1`).\n\n### Details\n\nvLLM uses an `assert` statement at [`vllm/model_executor/layers/pooler/activations.py:48`](https://github.com/vllm-project/vllm/blob/main/vllm/model_executor/layers/pooler/activations.py#L48) as its sole security control to restrict which activation functions can be loaded from a HuggingFace model\u0027s `config.json`:\n\n```python\n# vllm/model_executor/layers/pooler/activations.py:35-53\nfunction_name: str | None = None\nif (\n    hasattr(config, \"sentence_transformers\")\n    and \"activation_fn\" in config.sentence_transformers\n):\n    function_name = config.sentence_transformers[\"activation_fn\"]\nelif (\n    hasattr(config, \"sbert_ce_default_activation_function\")\n    and config.sbert_ce_default_activation_function is not None\n):\n    function_name = config.sbert_ce_default_activation_function\n\nif function_name is not None:\n    assert function_name.startswith(\"torch.nn.modules.\"), (\n        \"Loading of activation functions is restricted to \"\n        \"torch.nn.modules for security reasons\"\n    )\n    fn = resolve_obj_by_qualname(function_name)()\n```\n\nPython\u0027s `assert` statements are stripped at compile time when running in optimized mode (`python -O` or `PYTHONOPTIMIZE=1`). When the assert is absent, the attacker-controlled `function_name` from the model\u0027s `config.json` is passed directly to [`resolve_obj_by_qualname()`](https://github.com/vllm-project/vllm/blob/main/vllm/utils/import_utils.py#L106) \u2014 an unrestricted import gadget:\n\n```python\ndef resolve_obj_by_qualname(qualname: str) -\u003e Any:\n    module_name, obj_name = qualname.rsplit(\".\", 1)\n    module = importlib.import_module(module_name)\n    return getattr(module, obj_name)\n```\n\nThis is the same vulnerability class as **CVE-2017-1000433** (pysaml2 assert-based auth bypass), flagged by Bandit B101 and Ruff S101, and the reason Django proactively replaced all assert-based security checks (ticket #32508).\n\n**Attacker-controlled input sources:**\n- `config.sentence_transformers[\"activation_fn\"]` (line 40)\n- `config.sbert_ce_default_activation_function` (line 45)\n\n**Affected call sites** \u2014 `get_act_fn()` is called via `resolve_classifier_act_fn()` from:\n- `vllm/model_executor/layers/pooler/seqwise/poolers.py:122` \u2014 SequencePooler\n- `vllm/model_executor/layers/pooler/tokwise/poolers.py:130` \u2014 TokenPooler\n\n**Broader systemic risk:** `resolve_obj_by_qualname` is called from ~20 locations across the codebase with no validation of its own. Any future caller feeding user-controlled input to it without validation creates the same vulnerability class.\n\n**Suggested fix:** Replace the `assert` with an explicit conditional raise:\n\n```python\nif not function_name.startswith(\"torch.nn.modules.\"):\n    raise ValueError(\n        \"Loading of activation functions is restricted to \"\n        \"torch.nn.modules for security reasons\"\n    )\n```\n\n### Impact\n\n**Arbitrary code execution.** A malicious model author publishes a HuggingFace model with a crafted `config.json`. When a victim loads this model with vLLM running under `python -O` or `PYTHONOPTIMIZE=1`, arbitrary code executes during model initialization with the privileges of the vLLM process.\n\nThe attack requires:\n1. Victim loads a malicious model from HuggingFace (user interaction)\n2. vLLM runs under `python -O` or `PYTHONOPTIMIZE=1` (documented in production use)\n3. Model uses a cross-encoder architecture (e.g. BERT or RoBERTa with sequence classification)\n\n**Coordinated disclosure note:** This vulnerability was also reported via huntr.com on April 2, 2026 (https://huntr.com/bounties/dcb05b04-e625-41e7-adbc-bbae0cc2d64c). A GitHub Security Advisory was also filed because it is vLLM\u0027s stated preferred disclosure channel per SECURITY.md.\n\n### Fix\n\nA fix for this was introduced in this commit: https://github.com/vllm-project/vllm/commit/b3c7ffcab82c2439726f8cb213800f6f38c023d3",
  "id": "GHSA-q8gq-377p-jq3r",
  "modified": "2026-06-16T17:34:49Z",
  "published": "2026-06-16T17:34:49Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-q8gq-377p-jq3r"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/commit/b3c7ffcab82c2439726f8cb213800f6f38c023d3"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/vllm-project/vllm"
    },
    {
      "type": "WEB",
      "url": "https://huntr.com/bounties/dcb05b04-e625-41e7-adbc-bbae0cc2d64c"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "vLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arbitrary Code Execution"
}

{
  "document": {
    "aggregate_severity": {
      "text": "mittel"
    },
    "category": "csaf_base",
    "csaf_version": "2.0",
    "distribution": {
      "tlp": {
        "label": "WHITE",
        "url": "https://www.first.org/tlp/"
      }
    },
    "lang": "de-DE",
    "notes": [
      {
        "category": "legal_disclaimer",
        "text": "Das BSI ist als Anbieter f\u00fcr die eigenen, zur Nutzung bereitgestellten Inhalte nach den allgemeinen Gesetzen verantwortlich. Nutzerinnen und Nutzer sind jedoch daf\u00fcr verantwortlich, die Verwendung und/oder die Umsetzung der mit den Inhalten bereitgestellten Informationen sorgf\u00e4ltig im Einzelfall zu pr\u00fcfen."
      },
      {
        "category": "description",
        "text": "Open Source vLLM ist eine Open-Source-Bibliothek f\u00fcr schnelle und effiziente Inferenz von Large Language Models (LLMs).",
        "title": "Produktbeschreibung"
      },
      {
        "category": "summary",
        "text": "Ein entfernter, anonymer Angreifer kann eine Schwachstelle in vllm ausnutzen, um beliebigen Programmcode auszuf\u00fchren.",
        "title": "Angriff"
      },
      {
        "category": "general",
        "text": "- Linux\n- UNIX",
        "title": "Betroffene Betriebssysteme"
      }
    ],
    "publisher": {
      "category": "other",
      "contact_details": "csaf-provider@cert-bund.de",
      "name": "Bundesamt f\u00fcr Sicherheit in der Informationstechnik",
      "namespace": "https://www.bsi.bund.de"
    },
    "references": [
      {
        "category": "self",
        "summary": "WID-SEC-W-2026-1911 - CSAF Version",
        "url": "https://wid.cert-bund.de/.well-known/csaf/white/2026/wid-sec-w-2026-1911.json"
      },
      {
        "category": "self",
        "summary": "WID-SEC-2026-1911 - Portal Version",
        "url": "https://wid.cert-bund.de/portal/wid/securityadvisory?name=WID-SEC-2026-1911"
      },
      {
        "category": "external",
        "summary": "GitHub Security Advisory GHSA-q8gq-377p-jq3r vom 2026-06-14",
        "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-q8gq-377p-jq3r"
      }
    ],
    "source_lang": "en-US",
    "title": "vllm: Schwachstelle erm\u00f6glicht Codeausf\u00fchrung",
    "tracking": {
      "current_release_date": "2026-06-14T22:00:00.000+00:00",
      "generator": {
        "date": "2026-06-15T08:59:51.974+00:00",
        "engine": {
          "name": "BSI-WID",
          "version": "1.6.0"
        }
      },
      "id": "WID-SEC-W-2026-1911",
      "initial_release_date": "2026-06-14T22:00:00.000+00:00",
      "revision_history": [
        {
          "date": "2026-06-14T22:00:00.000+00:00",
          "number": "1",
          "summary": "Initiale Fassung"
        }
      ],
      "status": "final",
      "version": "1"
    }
  },
  "product_tree": {
    "branches": [
      {
        "branches": [
          {
            "branches": [
              {
                "category": "product_version_range",
                "name": "\u003c0.22.0",
                "product": {
                  "name": "Open Source vllm \u003c0.22.0",
                  "product_id": "T055350"
                }
              },
              {
                "category": "product_version",
                "name": "0.22.0",
                "product": {
                  "name": "Open Source vllm 0.22.0",
                  "product_id": "T055350-fixed",
                  "product_identification_helper": {
                    "cpe": "cpe:/a:vllm:vllm:0.22.0"
                  }
                }
              }
            ],
            "category": "product_name",
            "name": "vllm"
          }
        ],
        "category": "vendor",
        "name": "Open Source"
      }
    ]
  },
  "vulnerabilities": [
    {
      "cve": "CVE-2026-41523",
      "product_status": {
        "known_affected": [
          "T055350"
        ]
      },
      "release_date": "2026-06-14T22:00:00.000+00:00",
      "title": "CVE-2026-41523"
    }
  ]
}