Vulnerability-Lookup

GHSA-7972-PG2X-XR59

Vulnerability from github – Published: 2026-03-27 15:27 – Updated: 2026-03-27 15:27

Summary

vLLM has Hardcoded Trust Override in Model Files Enables RCE Despite Explicit User Opt-Out

Details

Summary

Two model implementation files hardcode trust_remote_code=True when loading sub-components, bypassing the user's explicit --trust-remote-code=False security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code trust.

### Details

Affected files (latest main branch):

vllm/model_executor/models/nemotron_vl.py:430 ```python vision_model = AutoModel.from_config(config.vision_config, trust_remote_code=True)


  2. vllm/model_executor/models/kimi_k25.py:177

```python
  cached_get_image_processor(self.ctx.model_config.model, trust_remote_code=True)

Both pass a hardcoded trust_remote_code=True to HuggingFace API calls, overriding the user's global --trust-remote-code=False setting.

Relation to prior CVEs: - CVE-2025-66448 fixed auto_map resolution in vllm/transformers_utils/config.py (config loading path) - CVE-2026-22807 fixed broader auto_map at startup - Both fixes are present in the current code. These hardcoded instances in model files survived both patches — different code paths.

Impact

Remote code execution. An attacker can craft a malicious model repository that executes arbitrary Python code when loaded by vLLM, even when the user has explicitly set --trust-remote-code=False. This undermines the security guarantee that trust_remote_code=False is intended to provide.

Remediation: Replace hardcoded trust_remote_code=True with self.config.model_config.trust_remote_code in both files. Raise a clear error if the model component requires remote code but the user hasn't opted in.

Severity ?

8.8 (High)


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

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "vllm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0.10.1"
            },
            {
              "fixed": "0.18.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-27893"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-693"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-03-27T15:27:20Z",
    "nvd_published_at": "2026-03-27T00:16:22Z",
    "severity": "HIGH"
  },
  "details": "### Summary\n\n  Two model implementation files hardcode `trust_remote_code=True` when loading sub-components, bypassing the user\u0027s explicit `--trust-remote-code=False` security opt-out. This enables remote code execution via malicious model\n  repositories even when the user has explicitly disabled remote code trust.\n\n  ### Details\n\n  **Affected files (latest main branch):**\n\n  1. `vllm/model_executor/models/nemotron_vl.py:430`\n  ```python\n  vision_model = AutoModel.from_config(config.vision_config, trust_remote_code=True)\n```\n\n  2. vllm/model_executor/models/kimi_k25.py:177\n \n```python\n  cached_get_image_processor(self.ctx.model_config.model, trust_remote_code=True)\n```\n\n  Both pass a hardcoded trust_remote_code=True to HuggingFace API calls, overriding the user\u0027s global --trust-remote-code=False setting.\n\n  Relation to prior CVEs:\n  - CVE-2025-66448 fixed auto_map resolution in vllm/transformers_utils/config.py (config loading path)\n  - CVE-2026-22807 fixed broader auto_map at startup\n  - Both fixes are present in the current code. These hardcoded instances in model files survived both patches \u2014 different code paths.\n\n### Impact\n\n  Remote code execution. An attacker can craft a malicious model repository that executes arbitrary Python code when loaded by vLLM, even when the user has explicitly set --trust-remote-code=False. This undermines the security guarantee\n  that trust_remote_code=False is intended to provide.\n\n  Remediation: Replace hardcoded trust_remote_code=True with self.config.model_config.trust_remote_code in both files. Raise a clear error if the model component requires remote code but the user hasn\u0027t opted in.",
  "id": "GHSA-7972-pg2x-xr59",
  "modified": "2026-03-27T15:27:20Z",
  "published": "2026-03-27T15:27:20Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-27893"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/pull/36192"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/vllm-project/vllm"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "vLLM has Hardcoded Trust Override in Model Files Enables RCE Despite Explicit User Opt-Out"
}

CVE-2026-27893 (GCVE-0-2026-27893)

Vulnerability from cvelistv5 – Published: 2026-03-26 23:56 – Updated: 2026-03-27 13:52

Title

vLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out

Summary

vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.18.0, two model implementation files hardcode `trust_remote_code=True` when loading sub-components, bypassing the user's explicit `--trust-remote-code=False` security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code trust. Version 0.18.0 patches the issue.

Severity ?

8.8 (High)


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

CWE

CWE-693 - Protection Mechanism Failure

Assigner

GitHub_M

References

URL

Tags

	https://github.com/vllm-project/vllm/security/adv…	x_refsource_CONFIRM
	https://github.com/vllm-project/vllm/pull/36192	x_refsource_MISC
	https://github.com/vllm-project/vllm/commit/00bd0…	x_refsource_MISC

Impacted products

	Vendor	Product	Version
	vllm-project	vllm	Affected: >= 0.10.1, < 0.18.0

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-27893",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-03-27T13:26:41.908182Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-03-27T13:52:33.526Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "vllm",
          "vendor": "vllm-project",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 0.10.1, \u003c 0.18.0"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.18.0, two model implementation files hardcode `trust_remote_code=True` when loading sub-components, bypassing the user\u0027s explicit `--trust-remote-code=False` security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code trust. Version 0.18.0 patches the issue."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 8.8,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-693",
              "description": "CWE-693: Protection Mechanism Failure",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-03-26T23:56:53.579Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59"
        },
        {
          "name": "https://github.com/vllm-project/vllm/pull/36192",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/pull/36192"
        },
        {
          "name": "https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72"
        }
      ],
      "source": {
        "advisory": "GHSA-7972-pg2x-xr59",
        "discovery": "UNKNOWN"
      },
      "title": "vLLM\u0027s hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-27893",
    "datePublished": "2026-03-26T23:56:53.579Z",
    "dateReserved": "2026-02-24T15:19:29.717Z",
    "dateUpdated": "2026-03-27T13:52:33.526Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

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.

Detection rules are retrieved from Rulezet.

Action not permitted

GHSA-7972-PG2X-XR59

Summary

Impact

CVE-2026-27893 (GCVE-0-2026-27893)

Tags

Sightings

Nomenclature