{"id":"CVE-2025-66448","aliases":["GHSA-8fr4-5q9j-m8gm","PYSEC-2026-2015"],"summary":"vLLM vulnerable to remote code execution via transformers_utils/get_config","published_at":"2025-12-01T22:45:42.566Z","modified_at":"2026-07-17T16:30:30.600907Z","products":[],"rating":{"severity":"high","score":7.5,"vector":"CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H","attack_path":"internet_authenticated","user_interaction":false,"malicious":false,"red_hat":"Important","vendor_ratings":[{"source":"Red Hat","rating":"Important"}]},"fix_available":false,"kev":{"listed":false,"ransomware":false},"public_exploit":false,"exploits":[],"epss":{"score":0.007079999893903732,"percentile":0.5421900153160095,"date":"2026-11-19T00:00:00Z"},"priority":8.5,"details":"vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.11.1, vllm has a critical remote code execution vector in a config class named Nemotron_Nano_VL_Config. When vllm loads a model config that contains an auto_map entry, the config class resolves that mapping with get_class_from_dynamic_module(...) and immediately instantiates the returned class. This fetches and executes Python from the remote repository referenced in the auto_map string. Crucially, this happens even when the caller explicitly sets trust_remote_code=False in vllm.transformers_utils.config.get_config. In practice, an attacker can publish a benign-looking frontend repo whose config.json points via auto_map to a separate malicious backend repo; loading the frontend will silently run the backend’s code on the victim host. This vulnerability is fixed in 0.11.1.","affected_stack":[],"affected_other":[{"ecosystem":"CVE","package":"vllm-project/vllm","versions":["< 0.11.1"],"provider":"cvelistv5","source":"CVE-2025-66448","relation":"self"},{"ecosystem":"NVD","package":"vllm:vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.11.1"}]}],"fixed":["0.11.1"],"provider":"nvd","source":"CVE-2025-66448","relation":"self"},{"ecosystem":"PyPI","package":"vllm","purl":"pkg:pypi/vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.11.1"}]}],"versions":["0.0.1","0.1.0","0.1.1","0.1.2","0.1.3","0.1.4","0.1.5","0.1.6","0.1.7","0.10.0","0.10.1","0.10.1.1","0.10.2","0.11.0","0.2.0","0.2.1","0.2.1.post1","0.2.2","0.2.3","0.2.4","0.2.5","0.2.6","0.2.7","0.3.0","0.3.1","0.3.2","0.3.3","0.4.0","0.4.0.post1","0.4.1","0.4.2","0.4.3","0.5.0","0.5.0.post1","0.5.1","0.5.2","0.5.3","0.5.3.post1","0.5.4","0.5.5","0.6.0","0.6.1","0.6.1.post1","0.6.1.post2","0.6.2","0.6.3","0.6.3.post1","0.6.4","0.6.4.post1","0.6.5","0.6.6","0.6.6.post1","0.7.0","0.7.1","0.7.2","0.7.3","0.8.0","0.8.1","0.8.2","0.8.3","0.8.4","0.8.5","0.8.5.post1","0.9.0","0.9.0.1","0.9.1","0.9.2"],"fixed":["0.11.1"],"provider":"osv","source":"GHSA-8fr4-5q9j-m8gm","relation":"self"},{"ecosystem":"PyPI","package":"vllm","purl":"pkg:pypi/vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.11.1"}]}],"versions":["0.0.1","0.1.0","0.1.1","0.1.2","0.1.3","0.1.4","0.1.5","0.1.6","0.1.7","0.10.0","0.10.1","0.10.1.1","0.10.2","0.11.0","0.2.0","0.2.1","0.2.1.post1","0.2.2","0.2.3","0.2.4","0.2.5","0.2.6","0.2.7","0.3.0","0.3.1","0.3.2","0.3.3","0.4.0","0.4.0.post1","0.4.1","0.4.2","0.4.3","0.5.0","0.5.0.post1","0.5.1","0.5.2","0.5.3","0.5.3.post1","0.5.4","0.5.5","0.6.0","0.6.1","0.6.1.post1","0.6.1.post2","0.6.2","0.6.3","0.6.3.post1","0.6.4","0.6.4.post1","0.6.5","0.6.6","0.6.6.post1","0.7.0","0.7.1","0.7.2","0.7.3","0.8.0","0.8.1","0.8.2","0.8.3","0.8.4","0.8.5","0.8.5.post1","0.9.0","0.9.0.1","0.9.1","0.9.2"],"fixed":["0.11.1"],"provider":"osv","source":"PYSEC-2026-2015","relation":"self"}],"product_status":[{"vendor":"Red Hat","product":"Red Hat AI Inference Server 3.2","cpe":"cpe:/a:redhat:ai_inference_server:3.2::el9","status":"fixed","packages":["rhaiis"],"package_count":1,"fixed":[],"advisories":["RHSA-2025:23078","RHSA-2025:23079","RHSA-2025:23080","RHSA-2025:23204","RHSA-2025:23205","RHSA-2025:23209","RHSA-2025:23449","RHSA-2026:3461","RHSA-2026:3462"],"provider":"redhat-vex","source":"CVE-2025-66448"},{"vendor":"Red Hat","product":"Red Hat AI Inference Server 3.3","cpe":"cpe:/a:redhat:ai_inference_server:3.3::el9","status":"fixed","packages":["rhaiis/vllm-spyre-rhel9"],"package_count":1,"fixed":[],"advisories":["RHSA-2026:30087"],"provider":"redhat-vex","source":"CVE-2025-66448"},{"vendor":"Red Hat","product":"Red Hat Enterprise Linux AI (RHEL AI)","cpe":"cpe:/a:redhat:enterprise_linux_ai:1","status":"affected","packages":["rhelai1/bootc-amd-rhel9","rhelai1/bootc-aws-nvidia-rhel9","rhelai1/bootc-azure-amd-rhel9","rhelai1/bootc-azure-nvidia-rhel9","rhelai1/bootc-gcp-nvidia-rhel9","rhelai1/bootc-intel-rhel9","rhelai1/bootc-nvidia-rhel9","rhelai1/instructlab-amd-rhel9","rhelai1/instructlab-intel-rhel9","rhelai1/instructlab-nvidia-rhel9"],"package_count":10,"fixed":[],"advisories":[],"note":"Will not fix","provider":"redhat-vex","source":"CVE-2025-66448"},{"vendor":"Red Hat","product":"Red Hat Enterprise Linux AI (RHEL AI) 3","cpe":"cpe:/a:redhat:enterprise_linux_ai:3","status":"affected","packages":["rhelai3/bootc-aws-cuda-rhel9","rhelai3/bootc-azure-cuda-rhel9","rhelai3/bootc-cuda-rhel9","rhelai3/bootc-gcp-cuda-rhel9"],"package_count":4,"fixed":[],"advisories":[],"note":"Will not fix","provider":"redhat-vex","source":"CVE-2025-66448"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI (RHOAI)","cpe":"cpe:/a:redhat:openshift_ai","status":"affected","packages":["rhoai/odh-vllm-cuda-rhel9","rhoai/odh-vllm-rocm-rhel9"],"package_count":2,"fixed":[],"advisories":[],"note":"Affected","provider":"redhat-vex","source":"CVE-2025-66448"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI 2.25","cpe":"cpe:/a:redhat:openshift_ai:2.25::el9","status":"fixed","packages":["rhoai"],"package_count":1,"fixed":[],"advisories":["RHSA-2026:3782"],"provider":"redhat-vex","source":"CVE-2025-66448"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI 2.25","cpe":"cpe:/a:redhat:openshift_ai:2.25::el9","status":"not_affected","packages":["rhoai"],"package_count":1,"fixed":[],"advisories":[],"note":"vulnerable_code_not_present","provider":"redhat-vex","source":"CVE-2025-66448"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI 3.3","cpe":"cpe:/a:redhat:openshift_ai:3.3::el9","status":"fixed","packages":["rhoai"],"package_count":1,"fixed":[],"advisories":["RHSA-2026:19712","RHSA-2026:3713"],"provider":"redhat-vex","source":"CVE-2025-66448"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI 3.3","cpe":"cpe:/a:redhat:openshift_ai:3.3::el9","status":"not_affected","packages":["rhoai"],"package_count":1,"fixed":[],"advisories":[],"note":"vulnerable_code_not_present","provider":"redhat-vex","source":"CVE-2025-66448"}],"records":[{"provider":"cvelistv5","source_id":"CVE-2025-66448","relation":"self","url":"https://www.cve.org/CVERecord?id=CVE-2025-66448","license":"CC-BY-4.0","published_at":"2025-12-01T22:45:42.566Z","modified_at":"2025-12-02T14:14:58.324Z","summary":"vLLM vulnerable to remote code execution via transformers_utils/get_config","details":"vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.11.1, vllm has a critical remote code execution vector in a config class named Nemotron_Nano_VL_Config. When vllm loads a model config that contains an auto_map entry, the config class resolves that mapping with get_class_from_dynamic_module(...) and immediately instantiates the returned class. This fetches and executes Python from the remote repository referenced in the auto_map string. Crucially, this happens even when the caller explicitly sets trust_remote_code=False in vllm.transformers_utils.config.get_config. In practice, an attacker can publish a benign-looking frontend repo whose config.json points via auto_map to a separate malicious backend repo; loading the frontend will silently run the backend’s code on the victim host. This vulnerability is fixed in 0.11.1.","severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H","source":"CVE-2025-66448"}],"affected":[{"ecosystem":"CVE","package":"vllm-project/vllm","versions":["< 0.11.1"],"provider":"cvelistv5","source":"CVE-2025-66448","relation":"self"}],"product_status":[],"references":[{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-8fr4-5q9j-m8gm"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/pull/28126"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/commit/ffb08379d8870a1a81ba82b72797f196838d0c86"}]},{"provider":"nvd","source_id":"CVE-2025-66448","relation":"self","url":"https://nvd.nist.gov/vuln/detail/CVE-2025-66448","severity":[],"affected":[{"ecosystem":"NVD","package":"vllm:vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.11.1"}]}],"fixed":["0.11.1"],"provider":"nvd","source":"CVE-2025-66448","relation":"self"}],"product_status":[],"references":[]},{"provider":"osv","source_id":"GHSA-8fr4-5q9j-m8gm","relation":"self","url":"https://osv.dev/vulnerability/GHSA-8fr4-5q9j-m8gm","license":"CC-BY-4.0","published_at":"2025-12-02T17:34:16Z","modified_at":"2026-07-17T16:30:30.600907Z","summary":"vLLM vulnerable to remote code execution via transformers_utils/get_config","details":"### Summary\n\n`vllm` has a critical remote code execution vector in a config class named `Nemotron_Nano_VL_Config`. When `vllm` loads a model config that contains an `auto_map` entry, the config class resolves that mapping with `get_class_from_dynamic_module(...)` and immediately instantiates the returned class. This fetches and executes Python from the remote repository referenced in the `auto_map` string. Crucially, this happens even when the caller explicitly sets `trust_remote_code=False` in `vllm.transformers_utils.config.get_config`. In practice, an attacker can publish a benign-looking frontend repo whose `config.json` points via `auto_map` to a separate malicious backend repo; loading the frontend will silently run the backend’s code on the victim host.\n\n### Details\n\nThe vulnerable code resolves and instantiates classes from `auto_map` entries without checking whether those entries point to a different repo or whether remote code execution is allowed.\n\n```python\nclass Nemotron_Nano_VL_Config(PretrainedConfig):\n    model_type = 'Llama_Nemotron_Nano_VL'\n\n    def __init__(self, **kwargs):\n        super().__init__(**kwargs)\n\n        if vision_config is not None:\n            assert \"auto_map\" in vision_config and \"AutoConfig\" in vision_config[\"auto_map\"]\n            # <-- vulnerable dynamic resolution + instantiation happens here\n            vision_auto_config = get_class_from_dynamic_module(*vision_config[\"auto_map\"][\"AutoConfig\"].split(\"--\")[::-1])\n            self.vision_config = vision_auto_config(**vision_config)\n        else:\n            self.vision_config = PretrainedConfig()\n```\n\n`get_class_from_dynamic_module(...)` is capable of fetching and importing code from the Hugging Face repo specified in the mapping. `trust_remote_code` is not enforced for this code path. As a result, a frontend repo can redirect the loader to any backend repo and cause code execution, bypassing the `trust_remote_code` guard.\n\n### Impact\n\nThis is a critical vulnerability because it breaks the documented `trust_remote_code` safety boundary in a core model-loading utility. The vulnerable code lives in a common loading path, so any application, service, CI job, or developer machine that uses `vllm`’s transformer utilities to load configs can be affected. The attack requires only two repos and no user interaction beyond loading the frontend model. A successful exploit can execute arbitrary commands on the host.\n\n### Fixes\n\n* https://github.com/vllm-project/vllm/pull/28126","severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H","source":"GHSA-8fr4-5q9j-m8gm"}],"affected":[{"ecosystem":"PyPI","package":"vllm","purl":"pkg:pypi/vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.11.1"}]}],"versions":["0.0.1","0.1.0","0.1.1","0.1.2","0.1.3","0.1.4","0.1.5","0.1.6","0.1.7","0.10.0","0.10.1","0.10.1.1","0.10.2","0.11.0","0.2.0","0.2.1","0.2.1.post1","0.2.2","0.2.3","0.2.4","0.2.5","0.2.6","0.2.7","0.3.0","0.3.1","0.3.2","0.3.3","0.4.0","0.4.0.post1","0.4.1","0.4.2","0.4.3","0.5.0","0.5.0.post1","0.5.1","0.5.2","0.5.3","0.5.3.post1","0.5.4","0.5.5","0.6.0","0.6.1","0.6.1.post1","0.6.1.post2","0.6.2","0.6.3","0.6.3.post1","0.6.4","0.6.4.post1","0.6.5","0.6.6","0.6.6.post1","0.7.0","0.7.1","0.7.2","0.7.3","0.8.0","0.8.1","0.8.2","0.8.3","0.8.4","0.8.5","0.8.5.post1","0.9.0","0.9.0.1","0.9.1","0.9.2"],"fixed":["0.11.1"],"provider":"osv","source":"GHSA-8fr4-5q9j-m8gm","relation":"self"}],"product_status":[],"references":[{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-8fr4-5q9j-m8gm"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2025-66448"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/pull/28126"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/commit/ffb08379d8870a1a81ba82b72797f196838d0c86"},{"type":"ADVISORY","url":"https://github.com/advisories/GHSA-8fr4-5q9j-m8gm"},{"type":"WEB","url":"https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2015.yaml"},{"type":"PACKAGE","url":"https://github.com/vllm-project/vllm"},{"type":"WEB","url":"https://pypi.org/project/vllm"}]},{"provider":"osv","source_id":"PYSEC-2026-2015","relation":"self","url":"https://osv.dev/vulnerability/PYSEC-2026-2015","license":"CC-BY-4.0","published_at":"2026-07-07T16:03:11.918128Z","modified_at":"2026-07-07T17:48:15.884423Z","summary":"vLLM vulnerable to remote code execution via transformers_utils/get_config","details":"### Summary\n\n`vllm` has a critical remote code execution vector in a config class named `Nemotron_Nano_VL_Config`. When `vllm` loads a model config that contains an `auto_map` entry, the config class resolves that mapping with `get_class_from_dynamic_module(...)` and immediately instantiates the returned class. This fetches and executes Python from the remote repository referenced in the `auto_map` string. Crucially, this happens even when the caller explicitly sets `trust_remote_code=False` in `vllm.transformers_utils.config.get_config`. In practice, an attacker can publish a benign-looking frontend repo whose `config.json` points via `auto_map` to a separate malicious backend repo; loading the frontend will silently run the backend’s code on the victim host.\n\n### Details\n\nThe vulnerable code resolves and instantiates classes from `auto_map` entries without checking whether those entries point to a different repo or whether remote code execution is allowed.\n\n```python\nclass Nemotron_Nano_VL_Config(PretrainedConfig):\n    model_type = 'Llama_Nemotron_Nano_VL'\n\n    def __init__(self, **kwargs):\n        super().__init__(**kwargs)\n\n        if vision_config is not None:\n            assert \"auto_map\" in vision_config and \"AutoConfig\" in vision_config[\"auto_map\"]\n            # <-- vulnerable dynamic resolution + instantiation happens here\n            vision_auto_config = get_class_from_dynamic_module(*vision_config[\"auto_map\"][\"AutoConfig\"].split(\"--\")[::-1])\n            self.vision_config = vision_auto_config(**vision_config)\n        else:\n            self.vision_config = PretrainedConfig()\n```\n\n`get_class_from_dynamic_module(...)` is capable of fetching and importing code from the Hugging Face repo specified in the mapping. `trust_remote_code` is not enforced for this code path. As a result, a frontend repo can redirect the loader to any backend repo and cause code execution, bypassing the `trust_remote_code` guard.\n\n### Impact\n\nThis is a critical vulnerability because it breaks the documented `trust_remote_code` safety boundary in a core model-loading utility. The vulnerable code lives in a common loading path, so any application, service, CI job, or developer machine that uses `vllm`’s transformer utilities to load configs can be affected. The attack requires only two repos and no user interaction beyond loading the frontend model. A successful exploit can execute arbitrary commands on the host.\n\n### Fixes\n\n* https://github.com/vllm-project/vllm/pull/28126","severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H","source":"PYSEC-2026-2015"}],"affected":[{"ecosystem":"PyPI","package":"vllm","purl":"pkg:pypi/vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.11.1"}]}],"versions":["0.0.1","0.1.0","0.1.1","0.1.2","0.1.3","0.1.4","0.1.5","0.1.6","0.1.7","0.10.0","0.10.1","0.10.1.1","0.10.2","0.11.0","0.2.0","0.2.1","0.2.1.post1","0.2.2","0.2.3","0.2.4","0.2.5","0.2.6","0.2.7","0.3.0","0.3.1","0.3.2","0.3.3","0.4.0","0.4.0.post1","0.4.1","0.4.2","0.4.3","0.5.0","0.5.0.post1","0.5.1","0.5.2","0.5.3","0.5.3.post1","0.5.4","0.5.5","0.6.0","0.6.1","0.6.1.post1","0.6.1.post2","0.6.2","0.6.3","0.6.3.post1","0.6.4","0.6.4.post1","0.6.5","0.6.6","0.6.6.post1","0.7.0","0.7.1","0.7.2","0.7.3","0.8.0","0.8.1","0.8.2","0.8.3","0.8.4","0.8.5","0.8.5.post1","0.9.0","0.9.0.1","0.9.1","0.9.2"],"fixed":["0.11.1"],"provider":"osv","source":"PYSEC-2026-2015","relation":"self"}],"product_status":[],"references":[{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-8fr4-5q9j-m8gm"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2025-66448"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/pull/28126"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/commit/ffb08379d8870a1a81ba82b72797f196838d0c86"},{"type":"PACKAGE","url":"https://github.com/vllm-project/vllm"},{"type":"PACKAGE","url":"https://pypi.org/project/vllm"},{"type":"ADVISORY","url":"https://github.com/advisories/GHSA-8fr4-5q9j-m8gm"}]},{"provider":"redhat-vex","source_id":"CVE-2025-66448","relation":"self","url":"https://access.redhat.com/security/cve/CVE-2025-66448","license":"CC-BY-4.0","published_at":"2025-12-01T22:45:42.566Z","modified_at":"2026-03-16T08:31:25Z","summary":"vllm: vLLM: Remote Code Execution via malicious model configuration","details":"A remote code execution vulnerability has been identified in vLLM. An attacker can exploit a weakness in the model loading process to silently fetch and run unauthorized, malicious Python code on the host system. This happens because the engine mistakenly executes code from a remote repository referenced in a model's configuration, even when explicit security measures are set to prevent it.","severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H","source":"CVE-2025-66448"},{"type":"Red Hat","score":"Important","source":"CVE-2025-66448"}],"affected":[],"product_status":[{"vendor":"Red Hat","product":"Red Hat AI Inference Server 3.2","cpe":"cpe:/a:redhat:ai_inference_server:3.2::el9","status":"fixed","packages":["rhaiis"],"package_count":1,"fixed":[],"advisories":["RHSA-2025:23078","RHSA-2025:23079","RHSA-2025:23080","RHSA-2025:23204","RHSA-2025:23205","RHSA-2025:23209","RHSA-2025:23449","RHSA-2026:3461","RHSA-2026:3462"],"provider":"redhat-vex","source":"CVE-2025-66448"},{"vendor":"Red Hat","product":"Red Hat AI Inference Server 3.3","cpe":"cpe:/a:redhat:ai_inference_server:3.3::el9","status":"fixed","packages":["rhaiis/vllm-spyre-rhel9"],"package_count":1,"fixed":[],"advisories":["RHSA-2026:30087"],"provider":"redhat-vex","source":"CVE-2025-66448"},{"vendor":"Red Hat","product":"Red Hat Enterprise Linux AI (RHEL AI)","cpe":"cpe:/a:redhat:enterprise_linux_ai:1","status":"affected","packages":["rhelai1/bootc-amd-rhel9","rhelai1/bootc-aws-nvidia-rhel9","rhelai1/bootc-azure-amd-rhel9","rhelai1/bootc-azure-nvidia-rhel9","rhelai1/bootc-gcp-nvidia-rhel9","rhelai1/bootc-intel-rhel9","rhelai1/bootc-nvidia-rhel9","rhelai1/instructlab-amd-rhel9","rhelai1/instructlab-intel-rhel9","rhelai1/instructlab-nvidia-rhel9"],"package_count":10,"fixed":[],"advisories":[],"note":"Will not fix","provider":"redhat-vex","source":"CVE-2025-66448"},{"vendor":"Red Hat","product":"Red Hat Enterprise Linux AI (RHEL AI) 3","cpe":"cpe:/a:redhat:enterprise_linux_ai:3","status":"affected","packages":["rhelai3/bootc-aws-cuda-rhel9","rhelai3/bootc-azure-cuda-rhel9","rhelai3/bootc-cuda-rhel9","rhelai3/bootc-gcp-cuda-rhel9"],"package_count":4,"fixed":[],"advisories":[],"note":"Will not fix","provider":"redhat-vex","source":"CVE-2025-66448"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI (RHOAI)","cpe":"cpe:/a:redhat:openshift_ai","status":"affected","packages":["rhoai/odh-vllm-cuda-rhel9","rhoai/odh-vllm-rocm-rhel9"],"package_count":2,"fixed":[],"advisories":[],"note":"Affected","provider":"redhat-vex","source":"CVE-2025-66448"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI 2.25","cpe":"cpe:/a:redhat:openshift_ai:2.25::el9","status":"fixed","packages":["rhoai"],"package_count":1,"fixed":[],"advisories":["RHSA-2026:3782"],"provider":"redhat-vex","source":"CVE-2025-66448"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI 2.25","cpe":"cpe:/a:redhat:openshift_ai:2.25::el9","status":"not_affected","packages":["rhoai"],"package_count":1,"fixed":[],"advisories":[],"note":"vulnerable_code_not_present","provider":"redhat-vex","source":"CVE-2025-66448"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI 3.3","cpe":"cpe:/a:redhat:openshift_ai:3.3::el9","status":"fixed","packages":["rhoai"],"package_count":1,"fixed":[],"advisories":["RHSA-2026:19712","RHSA-2026:3713"],"provider":"redhat-vex","source":"CVE-2025-66448"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI 3.3","cpe":"cpe:/a:redhat:openshift_ai:3.3::el9","status":"not_affected","packages":["rhoai"],"package_count":1,"fixed":[],"advisories":[],"note":"vulnerable_code_not_present","provider":"redhat-vex","source":"CVE-2025-66448"}],"references":[{"type":"WEB","url":"https://security.access.redhat.com/data/csaf/v2/vex/2025/cve-2025-66448.json"},{"type":"WEB","url":"https://access.redhat.com/security/cve/CVE-2025-66448"},{"type":"WEB","url":"https://bugzilla.redhat.com/show_bug.cgi?id=2418152"},{"type":"WEB","url":"https://www.cve.org/CVERecord?id=CVE-2025-66448"},{"type":"WEB","url":"https://nvd.nist.gov/vuln/detail/CVE-2025-66448"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/commit/ffb08379d8870a1a81ba82b72797f196838d0c86"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/pull/28126"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-8fr4-5q9j-m8gm"}]}],"references":[{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-8fr4-5q9j-m8gm"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/pull/28126"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/commit/ffb08379d8870a1a81ba82b72797f196838d0c86"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2025-66448"},{"type":"ADVISORY","url":"https://github.com/advisories/GHSA-8fr4-5q9j-m8gm"},{"type":"WEB","url":"https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2015.yaml"},{"type":"PACKAGE","url":"https://github.com/vllm-project/vllm"},{"type":"WEB","url":"https://pypi.org/project/vllm"},{"type":"WEB","url":"https://security.access.redhat.com/data/csaf/v2/vex/2025/cve-2025-66448.json"},{"type":"WEB","url":"https://access.redhat.com/security/cve/CVE-2025-66448"},{"type":"WEB","url":"https://bugzilla.redhat.com/show_bug.cgi?id=2418152"},{"type":"WEB","url":"https://www.cve.org/CVERecord?id=CVE-2025-66448"}],"sources":[{"provider":"cvelistv5","source_id":"CVE-2025-66448","url":"https://www.cve.org/CVERecord?id=CVE-2025-66448","license":"CC-BY-4.0","modified_at":"2025-12-02T14:14:58.324Z","relation":"self"},{"provider":"nvd","source_id":"CVE-2025-66448","url":"https://nvd.nist.gov/vuln/detail/CVE-2025-66448","relation":"self"},{"provider":"osv","source_id":"GHSA-8fr4-5q9j-m8gm","url":"https://osv.dev/vulnerability/GHSA-8fr4-5q9j-m8gm","license":"CC-BY-4.0","modified_at":"2026-07-17T16:30:30.600907Z","relation":"self"},{"provider":"osv","source_id":"PYSEC-2026-2015","url":"https://osv.dev/vulnerability/PYSEC-2026-2015","license":"CC-BY-4.0","modified_at":"2026-07-07T17:48:15.884423Z","relation":"self"},{"provider":"redhat-vex","source_id":"CVE-2025-66448","url":"https://access.redhat.com/security/cve/CVE-2025-66448","license":"CC-BY-4.0","modified_at":"2026-03-16T08:31:25Z","relation":"self"}]}
