{"id":"CVE-2026-55514","aliases":["GHSA-33cg-gxv8-3p8g","PYSEC-2026-2303"],"summary":"vLLM denial of service via prompt embeds on M-RoPE models","published_at":"2026-07-06T20:07:40.405Z","modified_at":"2026-09-10T03:50:51.451622Z","products":[],"rating":{"severity":"high","score":7.1,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N","attack_path":"internet_authenticated","user_interaction":false,"malicious":false,"red_hat":"Moderate","vendor_ratings":[{"source":"Red Hat","rating":"Moderate"}]},"fix_available":false,"kev":{"listed":false,"ransomware":false},"public_exploit":false,"exploits":[],"epss":{"score":0.006649999879300594,"percentile":0.5257400274276733,"date":"2026-11-19T00:00:00Z"},"priority":8.1,"details":"vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is authorized to make a /v1/completions request can make such a request and induce a crash. This issue is fixed in version 0.24.0.","affected_stack":[],"affected_other":[{"ecosystem":"CVE","package":"vllm-project/vllm","versions":[">= 0.12.0, < 0.24.0"],"provider":"cvelistv5","source":"CVE-2026-55514","relation":"self"},{"ecosystem":"NVD","package":"vllm:vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0.12.0"},{"fixed":"0.24.0"}]}],"fixed":["0.24.0"],"provider":"nvd","source":"CVE-2026-55514","relation":"self"},{"ecosystem":"PyPI","package":"vllm","purl":"pkg:pypi/vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0.12.0"},{"fixed":"0.24.0"}]}],"versions":["0.12.0","0.13.0","0.14.0","0.14.1","0.15.0","0.15.1","0.16.0","0.17.0","0.17.1","0.18.0","0.18.1","0.19.0","0.19.1","0.20.0","0.20.1","0.20.2","0.21.0","0.22.0","0.22.1","0.23.0"],"fixed":["0.24.0"],"provider":"osv","source":"GHSA-33cg-gxv8-3p8g","relation":"self"},{"ecosystem":"PyPI","package":"vllm","purl":"pkg:pypi/vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0.12.0"},{"fixed":"0.24.0"}]}],"versions":["0.12.0","0.13.0","0.14.0","0.14.1","0.15.0","0.15.1","0.16.0","0.17.0","0.17.1","0.18.0","0.18.1","0.19.0","0.19.1","0.20.0","0.20.1","0.20.2","0.21.0","0.22.0","0.22.1","0.23.0"],"fixed":["0.24.0"],"provider":"osv","source":"PYSEC-2026-2303","relation":"self"}],"product_status":[{"vendor":"Red Hat","product":"Red Hat AI Inference Server","cpe":"cpe:/a:redhat:ai_inference_server:3","status":"affected","packages":["rhaii/vllm-gaudi-rhel9","rhaii/vllm-neuron-rhel9","rhaii/vllm-tpu-rhel9","rhaiis/vllm-cpu-rhel9","rhaiis/vllm-cuda-rhel9","rhaiis/vllm-rocm-rhel9","rhaiis/vllm-tpu-rhel9"],"package_count":7,"fixed":[],"advisories":[],"note":"Fix deferred","provider":"redhat-vex","source":"CVE-2026-55514"},{"vendor":"Red Hat","product":"Red Hat AI Inference Server","cpe":"cpe:/a:redhat:ai_inference_server:3","status":"not_affected","packages":["rhaiis/vllm-neuron-rhel9","rhaiis/vllm-spyre-rhel9"],"package_count":2,"fixed":[],"advisories":[],"note":"vulnerable_code_not_present","provider":"redhat-vex","source":"CVE-2026-55514"},{"vendor":"Red Hat","product":"Red Hat AI Inference Server 3.4","cpe":"cpe:/a:redhat:ai_inference_server:3.4::el9","status":"fixed","packages":["rhaii/vllm-cpu-rhel9","rhaii/vllm-cuda-rhel9","rhaii/vllm-rocm-rhel9","rhaii/vllm-spyre-rhel9"],"package_count":4,"fixed":[],"advisories":["RHSA-2026:83112","RHSA-2026:83114","RHSA-2026:83120","RHSA-2026:83121"],"provider":"redhat-vex","source":"CVE-2026-55514"},{"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-gaudi-rhel9"],"package_count":1,"fixed":[],"advisories":[],"note":"Fix deferred","provider":"redhat-vex","source":"CVE-2026-55514"},{"vendor":"Red Hat","product":"Red Hat Enterprise Linux AI 3.4","cpe":"cpe:/a:redhat:enterprise_linux_ai:3.4::el9","status":"fixed","packages":["rhelai3/bootc-aws-cuda-rhel9","rhelai3/bootc-azure-cuda-rhel9","rhelai3/bootc-azure-rocm-rhel9","rhelai3/bootc-cuda-rhel9","rhelai3/bootc-gcp-cuda-rhel9","rhelai3/bootc-rocm-rhel9","rhelai3/disk-image-cuda-rhel9"],"package_count":7,"fixed":[],"advisories":["RHSA-2026:90432","RHSA-2026:90440"],"provider":"redhat-vex","source":"CVE-2026-55514"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI (RHOAI)","cpe":"cpe:/a:redhat:openshift_ai","status":"affected","packages":["rhoai/odh-llm-d-kv-cache-rhel9","rhoai/odh-vllm-gaudi-rhel9"],"package_count":2,"fixed":[],"advisories":[],"note":"Fix deferred","provider":"redhat-vex","source":"CVE-2026-55514"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI (RHOAI)","cpe":"cpe:/a:redhat:openshift_ai","status":"not_affected","packages":["rhoai/odh-kserve-agent-rhel9","rhoai/odh-kserve-controller-rhel9","rhoai/odh-kserve-router-rhel9","rhoai/odh-kserve-storage-initializer-rhel9"],"package_count":4,"fixed":[],"advisories":[],"note":"vulnerable_code_not_present","provider":"redhat-vex","source":"CVE-2026-55514"}],"records":[{"provider":"csaf-bsi","source_id":"WID-SEC-W-2026-2176","relation":"upstream","url":"https://wid.cert-bund.de/portal/wid/securityadvisory?name=WID-SEC-2026-2176","license":"TLP:CLEAR, mirroring permitted","published_at":"2026-07-01T22:00:00Z","modified_at":"2026-10-26T23:00:00Z","summary":"vllm: Mehrere Schwachstellen ermöglichen Denial of Service","details":"Ein Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um einen Denial of Service Angriff durchzuführen.\n\nOpen Source vLLM ist eine Open-Source-Bibliothek für schnelle und effiziente Inferenz von Large Language Models (LLMs).","severity":[{"type":"BSI","score":"mittel","source":"WID-SEC-W-2026-2176"}],"affected":[],"product_status":[],"references":[{"type":"WEB","url":"https://wid.cert-bund.de/.well-known/csaf/white/2026/wid-sec-w-2026-2176.json"},{"type":"WEB","url":"https://wid.cert-bund.de/portal/wid/securityadvisory?name=WID-SEC-2026-2176"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-33cg-gxv8-3p8g"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-8wr5-jm2h-8r4f"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-rwxx-mrjm-wc2m"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-v82g-2437-67m2"},{"type":"WEB","url":"https://access.redhat.com/errata/RHSA-2026:60363"},{"type":"WEB","url":"https://access.redhat.com/errata/RHSA-2026:61629"},{"type":"WEB","url":"https://access.redhat.com/errata/RHSA-2026:61627"},{"type":"WEB","url":"https://access.redhat.com/errata/RHSA-2026:70969"},{"type":"WEB","url":"https://access.redhat.com/errata/RHSA-2026:70965"},{"type":"WEB","url":"https://access.redhat.com/errata/RHSA-2026:70979"},{"type":"WEB","url":"https://access.redhat.com/errata/RHSA-2026:70995"},{"type":"WEB","url":"https://access.redhat.com/errata/RHSA-2026:76150"},{"type":"WEB","url":"https://access.redhat.com/errata/RHSA-2026:76149"},{"type":"WEB","url":"https://access.redhat.com/errata/RHSA-2026:90440"}]},{"provider":"cvelistv5","source_id":"CVE-2026-55514","relation":"self","url":"https://www.cve.org/CVERecord?id=CVE-2026-55514","license":"CC-BY-4.0","published_at":"2026-07-06T20:07:40.405Z","modified_at":"2026-07-06T20:46:52.405Z","summary":"vLLM denial of service via prompt embeds on M-RoPE models","details":"vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is authorized to make a /v1/completions request can make such a request and induce a crash. This issue is fixed in version 0.24.0.","severity":[{"type":"CVSS_V4","score":"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N","source":"CVE-2026-55514"}],"affected":[{"ecosystem":"CVE","package":"vllm-project/vllm","versions":[">= 0.12.0, < 0.24.0"],"provider":"cvelistv5","source":"CVE-2026-55514","relation":"self"}],"product_status":[],"references":[{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-33cg-gxv8-3p8g"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/pull/45252"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/commit/470229c37efaf69c86e8bc97482b0b1ff7551c65"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/releases/tag/v0.24.0"}]},{"provider":"nvd","source_id":"CVE-2026-55514","relation":"self","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-55514","severity":[],"affected":[{"ecosystem":"NVD","package":"vllm:vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0.12.0"},{"fixed":"0.24.0"}]}],"fixed":["0.24.0"],"provider":"nvd","source":"CVE-2026-55514","relation":"self"}],"product_status":[],"references":[]},{"provider":"osv","source_id":"GHSA-33cg-gxv8-3p8g","relation":"self","url":"https://osv.dev/vulnerability/GHSA-33cg-gxv8-3p8g","license":"CC-BY-4.0","published_at":"2026-07-20T19:13:07Z","modified_at":"2026-09-10T03:50:51.451622Z","summary":"vLLM denial of service via prompt embeds on M-RoPE models","details":"### Summary\n_Short summary of the problem. Make the impact and severity as clear as possible. For example: An unsafe deserialization vulnerability allows any unauthenticated user to execute arbitrary code on the server._\n\nSending a pure prompt embeds payload in a `/v1/completions` request with a model using M-RoPE causes the EngineCore to fail an assertion and fatally crash, shutting down the entire server application.\n\nAny remote user who is authorized to make a `/v1/completions` endpoint can trivially make such a request and induce a crash.\n\n### Details\n_Give all details on the vulnerability. Pointing to the incriminated source code is very helpful for the maintainer._\n\nIn commit [56669c1](https://github.com/vllm-project/vllm/commit/56669c1f293d5c53b6a19ddf2f78802fa9fff2c2), a simple assert intended to be a type-narrowing assert was added to the `_init_mrope_positions` method in `GPUModelRunner` (the offending line on main at the time of writing: https://github.com/vllm-project/vllm/blob/2d481f8a946ee0521872af0f098674a8ee01ce4a/vllm/v1/worker/gpu_model_runner.py#L1588-L1607).\n\n```python\nassert req_state.prompt_token_ids is not None, (\n            \"M-RoPE requires prompt_token_ids to be available.\"\n        )\n```\n\nThis type narrowing assert is to prevent mypy errors later in the function because `None` is not a valid type for `mrope_model.get_mrope_input_positions`. Unfortunately, this assertion is not always true. `/v1/completions` requests that specify `prompt=None` and `prompt_embeds=<not none>` will indeed create a CachedRequestState where `prompt_token_ids` is `None`. This triggers the assertion, which in turn crashes the EngineCore and the Server application.\n\n```\n(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167]   File \"/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py\", line 3997, in execute_model\n(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167]     deferred_state_corrections_fn = self._update_states(scheduler_output)\n(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167]                                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167]   File \"/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py\", line 1239, in _update_states\n(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167]     self._init_mrope_positions(req_state)\n(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167]   File \"/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py\", line 1582, in _init_mrope_positions\n(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167]     assert req_state.prompt_token_ids is not None, (\n(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n(EngineCore pid=351) ERROR 06-11 00:48:03 [core.py:1167] AssertionError: M-RoPE requires prompt_token_ids to be available.\n(APIServer pid=1) ERROR 06-11 00:48:03 [async_llm.py:704] AsyncLLM output_handler failed.\n(APIServer pid=1) ERROR 06-11 00:48:03 [async_llm.py:704] Traceback (most recent call last):\n(APIServer pid=1) ERROR 06-11 00:48:03 [async_llm.py:704]   File \"/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/async_llm.py\", line 660, in output_handler\n(APIServer pid=1) ERROR 06-11 00:48:03 [async_llm.py:704]     outputs = await engine_core.get_output_async()\n(APIServer pid=1) ERROR 06-11 00:48:03 [async_llm.py:704]               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n(APIServer pid=1) ERROR 06-11 00:48:03 [async_llm.py:704]   File \"/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core_client.py\", line 1030, in get_output_async\n(APIServer pid=1) ERROR 06-11 00:48:03 [async_llm.py:704]     raise self._format_exception(outputs) from None\n(APIServer pid=1) ERROR 06-11 00:48:03 [async_llm.py:704] vllm.v1.engine.exceptions.EngineDeadError: EngineCore encountered an issue. See stack trace (above) for the root cause.\n```\n\nAll requests using the `/v1/chat/completions` endpoints will have text/`prompt_token_ids` parts (corresponding to the chat template), and `prompt_embeds` parts are handled as mm_features. This method (rightly) filters out those `prompt_embeds` content parts as they are treated as text positions.\n\nA sufficient solution to type narrowing here without raising a fatal assertion is to instead replace the assertion with a using dummy token ids:\n\n```python\ndef _init_mrope_positions(self, req_state: CachedRequestState):\n    model = self.get_model()\n    assert supports_mrope(model), \"M-RoPE support is not implemented.\"\n    mrope_model = cast(SupportsMRoPE, model)\n\n    # Filter out prompt_embeds modality (text-only position info)\n    mrope_features = [\n        f for f in req_state.mm_features if f.modality != \"prompt_embeds\"\n    ]\n    \n    # Handle both token_ids and embeddings-only inputs\n    if req_state.prompt_token_ids is not None:\n        input_tokens = req_state.prompt_token_ids\n    elif req_state.prompt_embeds is not None:\n        # For text-only embeddings, dummy token IDs are safe since\n        # get_mrope_input_positions only uses len(input_tokens) when mm_features is empty\n        seq_len = req_state.prompt_embeds.shape[0]\n        input_tokens = list(range(seq_len))\n        # Verify no mm_features remain (should be true after prompt_embeds filter)\n        assert len(mrope_features) == 0, (\n            \"M-RoPE with prompt_embeds-only input should have no multimodal features\"\n        )\n    else:\n        raise ValueError(\n            \"M-RoPE requires either prompt_token_ids or prompt_embeds.\"\n        )\n\n    req_state.mrope_positions, req_state.mrope_position_delta = (\n        mrope_model.get_mrope_input_positions(\n            input_tokens,\n            mrope_features,\n        )\n    )\n```\n\nTechnically, in isolation, this method still crashes in the case where `req_state.prompt_token_ids is None and req_state.mm_features`, so the solution above still leaves that potential vector open. As far as can be determined, however, such a `req_state` is impossible in the first place in online mode, because it would require a `/v1/completions` request with `prompt_embeds` AND multimodal features, but the `/v1/completions` request schema does not expose multimodal inputs in any discernible way. Today, those are the only two endpoints with `prompt_embeds` support. \n\nWhen in offline mode, it *is technically* possible to directly create an `EngineCoreRequest` that has `prompt_embeds and not prompt_token_ids and mm_features`, and pass that to `LLM.generate`. That would trigger this same assertion, and no validation would prevent that combination. It is strongly suspected, though, that this combination would be undefined in any model that support M-RoPE, because it would not be possible to determine which token positions correspond to `mm_features`. The proposed solution above would end up not setting `req_state.mrope_positions` and `req_state.mrope_position_delta` in this scenario, which could result in undefined behavior.\n\n`prompt_embeds` is far more familiar here than M-RoPE, and it is understood that each model that supports it is responsible for defining its own `get_mrope_input_positions` which have varying implementations. There is insufficient knowledge to be prescriptive in how the two features should interact in the offline case, other than possibly raising a validation error earlier on preventing that combination (which would emulate the current assertion behavior). Regardless, in offline mode, the chances of a remote user being able to exploit this are slim-to-nil compared to the online case which is incredibly straightforward.\n\n### Impact\n_What kind of vulnerability is it? Who is impacted?_\n\n- Denial of Service caused by an incorrect assertion inside of the `GPUModelRunner` which causes a fatal EngineCore exception\n- Any configuration with `--enable-prompt-embeds` and M-RoPE-supported model is vulnerable\n- The attack is extremely easy from the remote attacker's perspective (copying the official `prompt_embeds` online mode docs examples almost-verbatim, accounting for model-name and connection details, of course, will induce a guaranteed shutdown)","severity":[{"type":"CVSS_V4","score":"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N","source":"GHSA-33cg-gxv8-3p8g"}],"affected":[{"ecosystem":"PyPI","package":"vllm","purl":"pkg:pypi/vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0.12.0"},{"fixed":"0.24.0"}]}],"versions":["0.12.0","0.13.0","0.14.0","0.14.1","0.15.0","0.15.1","0.16.0","0.17.0","0.17.1","0.18.0","0.18.1","0.19.0","0.19.1","0.20.0","0.20.1","0.20.2","0.21.0","0.22.0","0.22.1","0.23.0"],"fixed":["0.24.0"],"provider":"osv","source":"GHSA-33cg-gxv8-3p8g","relation":"self"}],"product_status":[],"references":[{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-33cg-gxv8-3p8g"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-55514"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/pull/45252"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/commit/470229c37efaf69c86e8bc97482b0b1ff7551c65"},{"type":"WEB","url":"https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2303.yaml"},{"type":"PACKAGE","url":"https://github.com/vllm-project/vllm"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/releases/tag/v0.24.0"}]},{"provider":"osv","source_id":"PYSEC-2026-2303","relation":"self","url":"https://osv.dev/vulnerability/PYSEC-2026-2303","license":"CC-BY-4.0","published_at":"2026-07-06T21:16:57.207Z","modified_at":"2026-07-13T07:15:46.624479Z","details":"vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is authorized to make a /v1/completions request can make such a request and induce a crash. This issue is fixed in version 0.24.0.","severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","source":"PYSEC-2026-2303"}],"affected":[{"ecosystem":"PyPI","package":"vllm","purl":"pkg:pypi/vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0.12.0"},{"fixed":"0.24.0"}]}],"versions":["0.12.0","0.13.0","0.14.0","0.14.1","0.15.0","0.15.1","0.16.0","0.17.0","0.17.1","0.18.0","0.18.1","0.19.0","0.19.1","0.20.0","0.20.1","0.20.2","0.21.0","0.22.0","0.22.1","0.23.0"],"fixed":["0.24.0"],"provider":"osv","source":"PYSEC-2026-2303","relation":"self"}],"product_status":[],"references":[{"type":"ADVISORY","url":"https://github.com/vllm-project/vllm/releases/tag/v0.24.0"},{"type":"ADVISORY","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-33cg-gxv8-3p8g"},{"type":"FIX","url":"https://github.com/vllm-project/vllm/commit/470229c37efaf69c86e8bc97482b0b1ff7551c65"},{"type":"FIX","url":"https://github.com/vllm-project/vllm/pull/45252"}]},{"provider":"redhat-vex","source_id":"CVE-2026-55514","relation":"self","url":"https://access.redhat.com/security/cve/CVE-2026-55514","license":"CC-BY-4.0","published_at":"2026-07-06T20:07:40.405Z","modified_at":"2026-07-08T05:00:55.602739Z","summary":"vllm: vLLM: Denial of Service via crafted prompt in /v1/completions request","details":"A flaw was found in vLLM, a library for Large Language Model (LLM) inference and serving. A remote attacker, authorized to make a /v1/completions request, can send a specially crafted prompt embeds payload. This action causes the EngineCore to fail an assertion and fatally crash, leading to a Denial of Service (DoS) for the entire server application.","severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","source":"CVE-2026-55514"},{"type":"Red Hat","score":"Moderate","source":"CVE-2026-55514"}],"affected":[],"product_status":[{"vendor":"Red Hat","product":"Red Hat AI Inference Server","cpe":"cpe:/a:redhat:ai_inference_server:3","status":"affected","packages":["rhaii/vllm-gaudi-rhel9","rhaii/vllm-neuron-rhel9","rhaii/vllm-tpu-rhel9","rhaiis/vllm-cpu-rhel9","rhaiis/vllm-cuda-rhel9","rhaiis/vllm-rocm-rhel9","rhaiis/vllm-tpu-rhel9"],"package_count":7,"fixed":[],"advisories":[],"note":"Fix deferred","provider":"redhat-vex","source":"CVE-2026-55514"},{"vendor":"Red Hat","product":"Red Hat AI Inference Server","cpe":"cpe:/a:redhat:ai_inference_server:3","status":"not_affected","packages":["rhaiis/vllm-neuron-rhel9","rhaiis/vllm-spyre-rhel9"],"package_count":2,"fixed":[],"advisories":[],"note":"vulnerable_code_not_present","provider":"redhat-vex","source":"CVE-2026-55514"},{"vendor":"Red Hat","product":"Red Hat AI Inference Server 3.4","cpe":"cpe:/a:redhat:ai_inference_server:3.4::el9","status":"fixed","packages":["rhaii/vllm-cpu-rhel9","rhaii/vllm-cuda-rhel9","rhaii/vllm-rocm-rhel9","rhaii/vllm-spyre-rhel9"],"package_count":4,"fixed":[],"advisories":["RHSA-2026:83112","RHSA-2026:83114","RHSA-2026:83120","RHSA-2026:83121"],"provider":"redhat-vex","source":"CVE-2026-55514"},{"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-gaudi-rhel9"],"package_count":1,"fixed":[],"advisories":[],"note":"Fix deferred","provider":"redhat-vex","source":"CVE-2026-55514"},{"vendor":"Red Hat","product":"Red Hat Enterprise Linux AI 3.4","cpe":"cpe:/a:redhat:enterprise_linux_ai:3.4::el9","status":"fixed","packages":["rhelai3/bootc-aws-cuda-rhel9","rhelai3/bootc-azure-cuda-rhel9","rhelai3/bootc-azure-rocm-rhel9","rhelai3/bootc-cuda-rhel9","rhelai3/bootc-gcp-cuda-rhel9","rhelai3/bootc-rocm-rhel9","rhelai3/disk-image-cuda-rhel9"],"package_count":7,"fixed":[],"advisories":["RHSA-2026:90432","RHSA-2026:90440"],"provider":"redhat-vex","source":"CVE-2026-55514"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI (RHOAI)","cpe":"cpe:/a:redhat:openshift_ai","status":"affected","packages":["rhoai/odh-llm-d-kv-cache-rhel9","rhoai/odh-vllm-gaudi-rhel9"],"package_count":2,"fixed":[],"advisories":[],"note":"Fix deferred","provider":"redhat-vex","source":"CVE-2026-55514"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI (RHOAI)","cpe":"cpe:/a:redhat:openshift_ai","status":"not_affected","packages":["rhoai/odh-kserve-agent-rhel9","rhoai/odh-kserve-controller-rhel9","rhoai/odh-kserve-router-rhel9","rhoai/odh-kserve-storage-initializer-rhel9"],"package_count":4,"fixed":[],"advisories":[],"note":"vulnerable_code_not_present","provider":"redhat-vex","source":"CVE-2026-55514"}],"references":[{"type":"WEB","url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-55514.json"},{"type":"WEB","url":"https://access.redhat.com/security/cve/CVE-2026-55514"},{"type":"WEB","url":"https://bugzilla.redhat.com/show_bug.cgi?id=2497504"},{"type":"WEB","url":"https://www.cve.org/CVERecord?id=CVE-2026-55514"},{"type":"WEB","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-55514"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/commit/470229c37efaf69c86e8bc97482b0b1ff7551c65"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/pull/45252"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/releases/tag/v0.24.0"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-33cg-gxv8-3p8g"}]}],"references":[{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-33cg-gxv8-3p8g"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/pull/45252"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/commit/470229c37efaf69c86e8bc97482b0b1ff7551c65"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/releases/tag/v0.24.0"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-55514"},{"type":"WEB","url":"https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2303.yaml"},{"type":"PACKAGE","url":"https://github.com/vllm-project/vllm"},{"type":"WEB","url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-55514.json"},{"type":"WEB","url":"https://access.redhat.com/security/cve/CVE-2026-55514"},{"type":"WEB","url":"https://bugzilla.redhat.com/show_bug.cgi?id=2497504"},{"type":"WEB","url":"https://www.cve.org/CVERecord?id=CVE-2026-55514"}],"sources":[{"provider":"csaf-bsi","source_id":"WID-SEC-W-2026-2176","url":"https://wid.cert-bund.de/portal/wid/securityadvisory?name=WID-SEC-2026-2176","license":"TLP:CLEAR, mirroring permitted","modified_at":"2026-10-26T23:00:00Z","relation":"upstream"},{"provider":"cvelistv5","source_id":"CVE-2026-55514","url":"https://www.cve.org/CVERecord?id=CVE-2026-55514","license":"CC-BY-4.0","modified_at":"2026-07-06T20:46:52.405Z","relation":"self"},{"provider":"nvd","source_id":"CVE-2026-55514","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-55514","relation":"self"},{"provider":"osv","source_id":"GHSA-33cg-gxv8-3p8g","url":"https://osv.dev/vulnerability/GHSA-33cg-gxv8-3p8g","license":"CC-BY-4.0","modified_at":"2026-09-10T03:50:51.451622Z","relation":"self"},{"provider":"osv","source_id":"PYSEC-2026-2303","url":"https://osv.dev/vulnerability/PYSEC-2026-2303","license":"CC-BY-4.0","modified_at":"2026-07-13T07:15:46.624479Z","relation":"self"},{"provider":"redhat-vex","source_id":"CVE-2026-55514","url":"https://access.redhat.com/security/cve/CVE-2026-55514","license":"CC-BY-4.0","modified_at":"2026-07-08T05:00:55.602739Z","relation":"self"}]}
