{"id":"CVE-2026-44513","aliases":["GHSA-98h9-4798-4q5v","PYSEC-2026-40"],"summary":"Diffusers: `trust_remote_code` bypass via `custom_pipeline` and local custom components","published_at":"2026-05-07T05:31:17Z","modified_at":"2026-09-10T03:51:05.118401Z","products":[],"rating":{"severity":"high","score":8.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","attack_path":"internet_unauthenticated","user_interaction":true,"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":0.010710000060498714,"percentile":0.6559299826622009,"date":"2026-11-19T00:00:00Z"},"priority":10.3,"details":"Diffusers is the a library for  pretrained diffusion models. Prior to 0.38.0, a trust_remote_code bypass in DiffusionPipeline.from_pretrained allows arbitrary remote code execution despite the user passing trust_remote_code=False (or omitting it, which is the default). The vulnerability has three variants, all sharing the same root cause — the trust_remote_code gate was implemented inside DiffusionPipeline.download() rather than at the actual dynamic-module load site, so any code path that bypassed or short-circuited download() also bypassed the security check. DiffusionPipeline.from_pretrained('repoA', custom_pipeline='attacker/repoB', trust_remote_code=False) — the gate evaluated against repoA's file list rather than repoB's, so repoB's pipeline.py was loaded and executed. DiffusionPipeline.from_pretrained('/local/snapshot', custom_pipeline='attacker/repoB', trust_remote_code=False) — the local-path branch never invoked download(), so the gate was never reached and remote code from repoB executed. DiffusionPipeline.from_pretrained('/local/snapshot', trust_remote_code=False) where the snapshot contains custom component files (e.g. unet/my_unet_model.py) referenced from model_index.json — same root cause; the local path skipped download() and custom component code executed. This vulnerability is fixed in 0.38.0.","affected_stack":[],"affected_other":[{"ecosystem":"CVE","package":"huggingface/diffusers","versions":["< 0.38.0"],"provider":"cvelistv5","source":"CVE-2026-44513","relation":"self"},{"ecosystem":"NVD","package":"huggingface:diffusers","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.38.0"}]}],"fixed":["0.38.0"],"provider":"nvd","source":"CVE-2026-44513","relation":"self"},{"ecosystem":"PyPI","package":"diffusers","purl":"pkg:pypi/diffusers","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.38.0"}]}],"versions":["0.0.1","0.0.2","0.0.3","0.0.4","0.1.0","0.1.1","0.1.2","0.1.3","0.10.0","0.10.1","0.10.2","0.11.0","0.11.1","0.12.0","0.12.1","0.13.0","0.13.1","0.14.0","0.15.0","0.15.1","0.16.0","0.16.1","0.17.0","0.17.1","0.18.0","0.18.1","0.18.2","0.19.0","0.19.1","0.19.2","0.19.3","0.2.0","0.2.1","0.2.2","0.2.3","0.2.4","0.20.0","0.20.1","0.20.2","0.21.0","0.21.1","0.21.2","0.21.3","0.21.4","0.22.0","0.22.1","0.22.2","0.22.3","0.23.0","0.23.1","0.24.0","0.25.0","0.25.1","0.26.0","0.26.1","0.26.2","0.26.3","0.27.0","0.27.1","0.27.2","0.28.0","0.28.1","0.28.2","0.29.0","0.29.1","0.29.2","0.3.0","0.30.0","0.30.1","0.30.2","0.30.3","0.31.0","0.32.0","0.32.1","0.32.2","0.33.0","0.33.1","0.34.0","0.35.0","0.35.1","0.35.2","0.36.0","0.37.0","0.37.1","0.4.0","0.4.1","0.4.2","0.5.0","0.5.1","0.6.0","0.7.0","0.7.1","0.7.2","0.8.0","0.8.1","0.9.0"],"fixed":["0.38.0"],"provider":"osv","source":"GHSA-98h9-4798-4q5v","relation":"self"},{"ecosystem":"PyPI","package":"diffusers","purl":"pkg:pypi/diffusers","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.38.0"}]}],"versions":["0.0.1","0.0.2","0.0.3","0.0.4","0.1.0","0.1.1","0.1.2","0.1.3","0.10.0","0.10.1","0.10.2","0.11.0","0.11.1","0.12.0","0.12.1","0.13.0","0.13.1","0.14.0","0.15.0","0.15.1","0.16.0","0.16.1","0.17.0","0.17.1","0.18.0","0.18.1","0.18.2","0.19.0","0.19.1","0.19.2","0.19.3","0.2.0","0.2.1","0.2.2","0.2.3","0.2.4","0.20.0","0.20.1","0.20.2","0.21.0","0.21.1","0.21.2","0.21.3","0.21.4","0.22.0","0.22.1","0.22.2","0.22.3","0.23.0","0.23.1","0.24.0","0.25.0","0.25.1","0.26.0","0.26.1","0.26.2","0.26.3","0.27.0","0.27.1","0.27.2","0.28.0","0.28.1","0.28.2","0.29.0","0.29.1","0.29.2","0.3.0","0.30.0","0.30.1","0.30.2","0.30.3","0.31.0","0.32.0","0.32.1","0.32.2","0.33.0","0.33.1","0.34.0","0.35.0","0.35.1","0.35.2","0.36.0","0.37.0","0.37.1","0.4.0","0.4.1","0.4.2","0.5.0","0.5.1","0.6.0","0.7.0","0.7.1","0.7.2","0.8.0","0.8.1","0.9.0"],"fixed":["0.38.0"],"provider":"osv","source":"PYSEC-2026-40","relation":"self"}],"product_status":[{"vendor":"Red Hat","product":"Red Hat AI Inference Server","cpe":"cpe:/a:redhat:ai_inference_server:3","status":"affected","packages":["rhaiis/vllm-tpu-rhel9"],"package_count":1,"fixed":[],"advisories":[],"note":"Will not fix","provider":"redhat-vex","source":"CVE-2026-44513"},{"vendor":"Red Hat","product":"Red Hat AI Inference Server","cpe":"cpe:/a:redhat:ai_inference_server:3","status":"not_affected","packages":["rhaiis/vllm-rocm-rhel9"],"package_count":1,"fixed":[],"advisories":[],"note":"vulnerable_code_not_present","provider":"redhat-vex","source":"CVE-2026-44513"},{"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"],"package_count":2,"fixed":[],"advisories":["RHSA-2026:69466","RHSA-2026:69467","RHSA-2026:70965","RHSA-2026:70979"],"provider":"redhat-vex","source":"CVE-2026-44513"},{"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-cuda-rhel9","rhelai3/bootc-gcp-cuda-rhel9","rhelai3/disk-image-cuda-rhel9"],"package_count":5,"fixed":[],"advisories":["RHSA-2026:76149","RHSA-2026:76150"],"provider":"redhat-vex","source":"CVE-2026-44513"},{"vendor":"Red Hat","product":"Red Hat Enterprise Linux AI 3.4","cpe":"cpe:/a:redhat:enterprise_linux_ai:3.4::el9","status":"not_affected","packages":["rhelai3/bootc-azure-rocm-rhel9","rhelai3/bootc-rocm-rhel9"],"package_count":2,"fixed":[],"advisories":[],"note":"vulnerable_code_not_present","provider":"redhat-vex","source":"CVE-2026-44513"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI (RHOAI)","cpe":"cpe:/a:redhat:openshift_ai","status":"affected","packages":["rhoai/odh-openvino-model-server-rhel9"],"package_count":1,"fixed":[],"advisories":[],"note":"Affected","provider":"redhat-vex","source":"CVE-2026-44513"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI (RHOAI)","cpe":"cpe:/a:redhat:openshift_ai","status":"not_affected","packages":["rhoai/odh-th06-cuda130-torch291-py312-rhel9"],"package_count":1,"fixed":[],"advisories":[],"note":"component_not_present","provider":"redhat-vex","source":"CVE-2026-44513"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI 3.4","cpe":"cpe:/a:redhat:openshift_ai:3.4::el9","status":"fixed","packages":["rhoai/odh-th06-cuda130-torch210-py312-rhel9","rhoai/odh-th06-rocm64-torch291-py312-rhel9","rhoai/odh-training-cuda128-torch29-py312-rhel9","rhoai/odh-training-rocm64-torch29-py312-rhel9"],"package_count":4,"fixed":[],"advisories":["RHSA-2026:60520"],"provider":"redhat-vex","source":"CVE-2026-44513"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI 3.4","cpe":"cpe:/a:redhat:openshift_ai:3.4::el9","status":"not_affected","packages":["rhoai/odh-ai-gateway-payload-processing-rhel9","rhoai/odh-automl-rhel9","rhoai/odh-autorag-rhel9","rhoai/odh-built-in-detector-rhel9","rhoai/odh-cli-rhel9","rhoai/odh-dashboard-rhel9","rhoai/odh-data-science-pipelines-argo-argoexec-rhel9","rhoai/odh-data-science-pipelines-argo-workflowcontroller-rhel9","rhoai/odh-data-science-pipelines-operator-controller-rhel9","rhoai/odh-eval-hub-rhel9","rhoai/odh-feast-operator-rhel9","rhoai/odh-feature-server-rhel9","rhoai/odh-fms-guardrails-orchestrator-rhel9","rhoai/odh-guardrails-detector-huggingface-runtime-rhel9","rhoai/odh-kf-notebook-controller-rhel9","rhoai/odh-kserve-agent-rhel9","rhoai/odh-kserve-autogluon-server-rhel9","rhoai/odh-kserve-controller-rhel9","rhoai/odh-kserve-llmisvc-controller-rhel9","rhoai/odh-kserve-router-rhel9","rhoai/odh-kserve-storage-initializer-rhel9","rhoai/odh-kube-auth-proxy-rhel9","rhoai/odh-kuberay-operator-controller-rhel9","rhoai/odh-llama-stack-core-rhel9","rhoai/odh-llama-stack-k8s-operator-rhel9"],"package_count":102,"fixed":[],"advisories":[],"note":"vulnerable_code_not_present","provider":"redhat-vex","source":"CVE-2026-44513"}],"records":[{"provider":"cvelistv5","source_id":"CVE-2026-44513","relation":"self","url":"https://www.cve.org/CVERecord?id=CVE-2026-44513","license":"CC-BY-4.0","published_at":"2026-05-14T16:26:03.907Z","modified_at":"2026-08-28T12:04:31.466Z","summary":"Diffusers: `trust_remote_code` bypass via `custom_pipeline` and local custom components","details":"Diffusers is the a library for  pretrained diffusion models. Prior to 0.38.0, a trust_remote_code bypass in DiffusionPipeline.from_pretrained allows arbitrary remote code execution despite the user passing trust_remote_code=False (or omitting it, which is the default). The vulnerability has three variants, all sharing the same root cause — the trust_remote_code gate was implemented inside DiffusionPipeline.download() rather than at the actual dynamic-module load site, so any code path that bypassed or short-circuited download() also bypassed the security check. DiffusionPipeline.from_pretrained('repoA', custom_pipeline='attacker/repoB', trust_remote_code=False) — the gate evaluated against repoA's file list rather than repoB's, so repoB's pipeline.py was loaded and executed. DiffusionPipeline.from_pretrained('/local/snapshot', custom_pipeline='attacker/repoB', trust_remote_code=False) — the local-path branch never invoked download(), so the gate was never reached and remote code from repoB executed. DiffusionPipeline.from_pretrained('/local/snapshot', trust_remote_code=False) where the snapshot contains custom component files (e.g. unet/my_unet_model.py) referenced from model_index.json — same root cause; the local path skipped download() and custom component code executed. This vulnerability is fixed in 0.38.0.","severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","source":"CVE-2026-44513"},{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","source":"redhat-SADP:CVE-2026-44513"}],"affected":[{"ecosystem":"CVE","package":"huggingface/diffusers","versions":["< 0.38.0"],"provider":"cvelistv5","source":"CVE-2026-44513","relation":"self"}],"product_status":[],"references":[{"type":"WEB","url":"https://github.com/huggingface/diffusers/security/advisories/GHSA-98h9-4798-4q5v"}]},{"provider":"nvd","source_id":"CVE-2026-44513","relation":"self","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-44513","severity":[],"affected":[{"ecosystem":"NVD","package":"huggingface:diffusers","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.38.0"}]}],"fixed":["0.38.0"],"provider":"nvd","source":"CVE-2026-44513","relation":"self"}],"product_status":[],"references":[]},{"provider":"osv","source_id":"GHSA-98h9-4798-4q5v","relation":"self","url":"https://osv.dev/vulnerability/GHSA-98h9-4798-4q5v","license":"CC-BY-4.0","published_at":"2026-05-07T05:31:17Z","modified_at":"2026-09-10T03:51:05.118401Z","summary":"Diffusers has a `trust_remote_code` bypass via `custom_pipeline` and local custom components","details":"### Impact\n\nA `trust_remote_code` bypass in `DiffusionPipeline.from_pretrained` allows arbitrary remote code execution despite the user passing `trust_remote_code=False` (or omitting it, which is the default). The vulnerability has three variants, all sharing the same root cause — the `trust_remote_code` gate was implemented inside `DiffusionPipeline.download()` rather than at the actual dynamic-module load site, so any code path that bypassed or short-circuited `download()` also bypassed the security check:\n\n1. **Cross-repo `custom_pipeline`.** `DiffusionPipeline.from_pretrained('repoA', custom_pipeline='attacker/repoB', trust_remote_code=False)` — the gate evaluated against `repoA`'s file list rather than `repoB`'s, so `repoB`'s `pipeline.py` was loaded and executed.\n2. **Local snapshot + Hub `custom_pipeline`.** `DiffusionPipeline.from_pretrained('/local/snapshot', custom_pipeline='attacker/repoB', trust_remote_code=False)` — the local-path branch never invoked `download()`, so the gate was never reached and remote code from `repoB` executed.\n3. **Local snapshot with custom components.** `DiffusionPipeline.from_pretrained('/local/snapshot', trust_remote_code=False)` where the snapshot contains custom component files (e.g. `unet/my_unet_model.py`) referenced from `model_index.json` — same root cause; the local path skipped `download()` and custom component code executed.\n\nSilent remote code execution on the victim's machine. Anyone calling `DiffusionPipeline.from_pretrained` with custom pipelines is impacted.\n\n### Patches\n\nYes. Fixed in **diffusers 0.38.0** via [PR #13448](https://github.com/huggingface/diffusers/pull/13448). All users on versions `< 0.38.0` should upgrade:\n\n```bash\npip install --upgrade \"diffusers>=0.38.0\"\n```\n\nThe fix moves the `trust_remote_code` gate out of `DiffusionPipeline.download()` and into `get_cached_module_file` in `src/diffusers/utils/dynamic_modules_utils.py`, which is the actual chokepoint for every dynamic module load (local, Hub, or community mirror). All three variants now raise `ValueError` instead of executing untrusted code.\n\n### Workarounds\n\nIf upgrading immediately is not possible:\n\n- Only call `from_pretrained` with `pretrained_model_name_or_path`, `custom_pipeline`, and local snapshot directories from fully trusted sources that have been audited.\n- Do not pass `custom_pipeline=` pointing at a Hub repository different from the primary `pretrained_model_name_or_path` before reading its `pipeline.py`.\n- Before calling `from_pretrained` on a local snapshot, inspect the snapshot for unexpected `*.py` files, especially under component subdirectories (`unet/`, `scheduler/`, etc.) and at the snapshot root.\n\nThese are mitigations, not fixes — the only complete remediation is upgrading to 0.38.0.\n\n### Resources\n\n- **Fix:** https://github.com/huggingface/diffusers/pull/13448\n- **Original issue:** https://github.com/huggingface/diffusers/issues/13446\n- **Release notes:** https://github.com/huggingface/diffusers/releases/tag/v0.38.0\n- **CWE-94:** https://cwe.mitre.org/data/definitions/94.html","severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","source":"GHSA-98h9-4798-4q5v"}],"affected":[{"ecosystem":"PyPI","package":"diffusers","purl":"pkg:pypi/diffusers","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.38.0"}]}],"versions":["0.0.1","0.0.2","0.0.3","0.0.4","0.1.0","0.1.1","0.1.2","0.1.3","0.10.0","0.10.1","0.10.2","0.11.0","0.11.1","0.12.0","0.12.1","0.13.0","0.13.1","0.14.0","0.15.0","0.15.1","0.16.0","0.16.1","0.17.0","0.17.1","0.18.0","0.18.1","0.18.2","0.19.0","0.19.1","0.19.2","0.19.3","0.2.0","0.2.1","0.2.2","0.2.3","0.2.4","0.20.0","0.20.1","0.20.2","0.21.0","0.21.1","0.21.2","0.21.3","0.21.4","0.22.0","0.22.1","0.22.2","0.22.3","0.23.0","0.23.1","0.24.0","0.25.0","0.25.1","0.26.0","0.26.1","0.26.2","0.26.3","0.27.0","0.27.1","0.27.2","0.28.0","0.28.1","0.28.2","0.29.0","0.29.1","0.29.2","0.3.0","0.30.0","0.30.1","0.30.2","0.30.3","0.31.0","0.32.0","0.32.1","0.32.2","0.33.0","0.33.1","0.34.0","0.35.0","0.35.1","0.35.2","0.36.0","0.37.0","0.37.1","0.4.0","0.4.1","0.4.2","0.5.0","0.5.1","0.6.0","0.7.0","0.7.1","0.7.2","0.8.0","0.8.1","0.9.0"],"fixed":["0.38.0"],"provider":"osv","source":"GHSA-98h9-4798-4q5v","relation":"self"}],"product_status":[],"references":[{"type":"WEB","url":"https://github.com/huggingface/diffusers/security/advisories/GHSA-98h9-4798-4q5v"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-44513"},{"type":"WEB","url":"https://github.com/huggingface/diffusers/issues/13446"},{"type":"WEB","url":"https://github.com/huggingface/diffusers/pull/13448"},{"type":"WEB","url":"https://github.com/huggingface/diffusers/commit/a37f6f8394ac2a7ee8360c3abea811efe54512b1"},{"type":"PACKAGE","url":"https://github.com/huggingface/diffusers"},{"type":"WEB","url":"https://github.com/huggingface/diffusers/releases/tag/v0.38.0"},{"type":"WEB","url":"https://github.com/pypa/advisory-database/tree/main/vulns/diffusers/PYSEC-2026-40.yaml"}]},{"provider":"osv","source_id":"PYSEC-2026-40","relation":"self","url":"https://osv.dev/vulnerability/PYSEC-2026-40","license":"CC-BY-4.0","published_at":"2026-05-14T17:16:22.903Z","modified_at":"2026-05-20T09:18:56.669156Z","details":"Diffusers is the a library for  pretrained diffusion models. Prior to 0.38.0, a trust_remote_code bypass in DiffusionPipeline.from_pretrained allows arbitrary remote code execution despite the user passing trust_remote_code=False (or omitting it, which is the default). The vulnerability has three variants, all sharing the same root cause — the trust_remote_code gate was implemented inside DiffusionPipeline.download() rather than at the actual dynamic-module load site, so any code path that bypassed or short-circuited download() also bypassed the security check. DiffusionPipeline.from_pretrained('repoA', custom_pipeline='attacker/repoB', trust_remote_code=False) — the gate evaluated against repoA's file list rather than repoB's, so repoB's pipeline.py was loaded and executed. DiffusionPipeline.from_pretrained('/local/snapshot', custom_pipeline='attacker/repoB', trust_remote_code=False) — the local-path branch never invoked download(), so the gate was never reached and remote code from repoB executed. DiffusionPipeline.from_pretrained('/local/snapshot', trust_remote_code=False) where the snapshot contains custom component files (e.g. unet/my_unet_model.py) referenced from model_index.json — same root cause; the local path skipped download() and custom component code executed. This vulnerability is fixed in 0.38.0.","severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","source":"PYSEC-2026-40"}],"affected":[{"ecosystem":"PyPI","package":"diffusers","purl":"pkg:pypi/diffusers","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.38.0"}]}],"versions":["0.0.1","0.0.2","0.0.3","0.0.4","0.1.0","0.1.1","0.1.2","0.1.3","0.10.0","0.10.1","0.10.2","0.11.0","0.11.1","0.12.0","0.12.1","0.13.0","0.13.1","0.14.0","0.15.0","0.15.1","0.16.0","0.16.1","0.17.0","0.17.1","0.18.0","0.18.1","0.18.2","0.19.0","0.19.1","0.19.2","0.19.3","0.2.0","0.2.1","0.2.2","0.2.3","0.2.4","0.20.0","0.20.1","0.20.2","0.21.0","0.21.1","0.21.2","0.21.3","0.21.4","0.22.0","0.22.1","0.22.2","0.22.3","0.23.0","0.23.1","0.24.0","0.25.0","0.25.1","0.26.0","0.26.1","0.26.2","0.26.3","0.27.0","0.27.1","0.27.2","0.28.0","0.28.1","0.28.2","0.29.0","0.29.1","0.29.2","0.3.0","0.30.0","0.30.1","0.30.2","0.30.3","0.31.0","0.32.0","0.32.1","0.32.2","0.33.0","0.33.1","0.34.0","0.35.0","0.35.1","0.35.2","0.36.0","0.37.0","0.37.1","0.4.0","0.4.1","0.4.2","0.5.0","0.5.1","0.6.0","0.7.0","0.7.1","0.7.2","0.8.0","0.8.1","0.9.0"],"fixed":["0.38.0"],"provider":"osv","source":"PYSEC-2026-40","relation":"self"}],"product_status":[],"references":[{"type":"EVIDENCE","url":"https://github.com/huggingface/diffusers/security/advisories/GHSA-98h9-4798-4q5v"}]},{"provider":"redhat-vex","source_id":"CVE-2026-44513","relation":"self","url":"https://access.redhat.com/security/cve/CVE-2026-44513","license":"CC-BY-4.0","published_at":"2026-05-14T16:26:03.907Z","modified_at":"2026-08-10T11:00:52.758843Z","summary":"Diffusers: Diffusers: Arbitrary remote code execution via `trust_remote_code` bypass","details":"A flaw was found in Diffusers, a library for pretrained diffusion models. A remote attacker could exploit a bypass in the `trust_remote_code` mechanism within the `DiffusionPipeline.from_pretrained` function. This vulnerability allows for arbitrary remote code execution, even when the user explicitly sets `trust_remote_code=False` or omits it. The issue stems from the security check being incorrectly placed, allowing malicious code to be loaded and executed by bypassing the intended security gate.","severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","source":"CVE-2026-44513"},{"type":"Red Hat","score":"Important","source":"CVE-2026-44513"}],"affected":[],"product_status":[{"vendor":"Red Hat","product":"Red Hat AI Inference Server","cpe":"cpe:/a:redhat:ai_inference_server:3","status":"affected","packages":["rhaiis/vllm-tpu-rhel9"],"package_count":1,"fixed":[],"advisories":[],"note":"Will not fix","provider":"redhat-vex","source":"CVE-2026-44513"},{"vendor":"Red Hat","product":"Red Hat AI Inference Server","cpe":"cpe:/a:redhat:ai_inference_server:3","status":"not_affected","packages":["rhaiis/vllm-rocm-rhel9"],"package_count":1,"fixed":[],"advisories":[],"note":"vulnerable_code_not_present","provider":"redhat-vex","source":"CVE-2026-44513"},{"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"],"package_count":2,"fixed":[],"advisories":["RHSA-2026:69466","RHSA-2026:69467","RHSA-2026:70965","RHSA-2026:70979"],"provider":"redhat-vex","source":"CVE-2026-44513"},{"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-cuda-rhel9","rhelai3/bootc-gcp-cuda-rhel9","rhelai3/disk-image-cuda-rhel9"],"package_count":5,"fixed":[],"advisories":["RHSA-2026:76149","RHSA-2026:76150"],"provider":"redhat-vex","source":"CVE-2026-44513"},{"vendor":"Red Hat","product":"Red Hat Enterprise Linux AI 3.4","cpe":"cpe:/a:redhat:enterprise_linux_ai:3.4::el9","status":"not_affected","packages":["rhelai3/bootc-azure-rocm-rhel9","rhelai3/bootc-rocm-rhel9"],"package_count":2,"fixed":[],"advisories":[],"note":"vulnerable_code_not_present","provider":"redhat-vex","source":"CVE-2026-44513"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI (RHOAI)","cpe":"cpe:/a:redhat:openshift_ai","status":"affected","packages":["rhoai/odh-openvino-model-server-rhel9"],"package_count":1,"fixed":[],"advisories":[],"note":"Affected","provider":"redhat-vex","source":"CVE-2026-44513"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI (RHOAI)","cpe":"cpe:/a:redhat:openshift_ai","status":"not_affected","packages":["rhoai/odh-th06-cuda130-torch291-py312-rhel9"],"package_count":1,"fixed":[],"advisories":[],"note":"component_not_present","provider":"redhat-vex","source":"CVE-2026-44513"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI 3.4","cpe":"cpe:/a:redhat:openshift_ai:3.4::el9","status":"fixed","packages":["rhoai/odh-th06-cuda130-torch210-py312-rhel9","rhoai/odh-th06-rocm64-torch291-py312-rhel9","rhoai/odh-training-cuda128-torch29-py312-rhel9","rhoai/odh-training-rocm64-torch29-py312-rhel9"],"package_count":4,"fixed":[],"advisories":["RHSA-2026:60520"],"provider":"redhat-vex","source":"CVE-2026-44513"},{"vendor":"Red Hat","product":"Red Hat OpenShift AI 3.4","cpe":"cpe:/a:redhat:openshift_ai:3.4::el9","status":"not_affected","packages":["rhoai/odh-ai-gateway-payload-processing-rhel9","rhoai/odh-automl-rhel9","rhoai/odh-autorag-rhel9","rhoai/odh-built-in-detector-rhel9","rhoai/odh-cli-rhel9","rhoai/odh-dashboard-rhel9","rhoai/odh-data-science-pipelines-argo-argoexec-rhel9","rhoai/odh-data-science-pipelines-argo-workflowcontroller-rhel9","rhoai/odh-data-science-pipelines-operator-controller-rhel9","rhoai/odh-eval-hub-rhel9","rhoai/odh-feast-operator-rhel9","rhoai/odh-feature-server-rhel9","rhoai/odh-fms-guardrails-orchestrator-rhel9","rhoai/odh-guardrails-detector-huggingface-runtime-rhel9","rhoai/odh-kf-notebook-controller-rhel9","rhoai/odh-kserve-agent-rhel9","rhoai/odh-kserve-autogluon-server-rhel9","rhoai/odh-kserve-controller-rhel9","rhoai/odh-kserve-llmisvc-controller-rhel9","rhoai/odh-kserve-router-rhel9","rhoai/odh-kserve-storage-initializer-rhel9","rhoai/odh-kube-auth-proxy-rhel9","rhoai/odh-kuberay-operator-controller-rhel9","rhoai/odh-llama-stack-core-rhel9","rhoai/odh-llama-stack-k8s-operator-rhel9"],"package_count":102,"fixed":[],"advisories":[],"note":"vulnerable_code_not_present","provider":"redhat-vex","source":"CVE-2026-44513"}],"references":[{"type":"WEB","url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-44513.json"},{"type":"WEB","url":"https://access.redhat.com/security/cve/CVE-2026-44513"},{"type":"WEB","url":"https://bugzilla.redhat.com/show_bug.cgi?id=2477507"},{"type":"WEB","url":"https://www.cve.org/CVERecord?id=CVE-2026-44513"},{"type":"WEB","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-44513"},{"type":"WEB","url":"https://github.com/huggingface/diffusers/security/advisories/GHSA-98h9-4798-4q5v"}]}],"references":[{"type":"WEB","url":"https://github.com/huggingface/diffusers/security/advisories/GHSA-98h9-4798-4q5v"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-44513"},{"type":"WEB","url":"https://github.com/huggingface/diffusers/issues/13446"},{"type":"WEB","url":"https://github.com/huggingface/diffusers/pull/13448"},{"type":"WEB","url":"https://github.com/huggingface/diffusers/commit/a37f6f8394ac2a7ee8360c3abea811efe54512b1"},{"type":"PACKAGE","url":"https://github.com/huggingface/diffusers"},{"type":"WEB","url":"https://github.com/huggingface/diffusers/releases/tag/v0.38.0"},{"type":"WEB","url":"https://github.com/pypa/advisory-database/tree/main/vulns/diffusers/PYSEC-2026-40.yaml"},{"type":"WEB","url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-44513.json"},{"type":"WEB","url":"https://access.redhat.com/security/cve/CVE-2026-44513"},{"type":"WEB","url":"https://bugzilla.redhat.com/show_bug.cgi?id=2477507"},{"type":"WEB","url":"https://www.cve.org/CVERecord?id=CVE-2026-44513"}],"sources":[{"provider":"cvelistv5","source_id":"CVE-2026-44513","url":"https://www.cve.org/CVERecord?id=CVE-2026-44513","license":"CC-BY-4.0","modified_at":"2026-08-28T12:04:31.466Z","relation":"self"},{"provider":"nvd","source_id":"CVE-2026-44513","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-44513","relation":"self"},{"provider":"osv","source_id":"GHSA-98h9-4798-4q5v","url":"https://osv.dev/vulnerability/GHSA-98h9-4798-4q5v","license":"CC-BY-4.0","modified_at":"2026-09-10T03:51:05.118401Z","relation":"self"},{"provider":"osv","source_id":"PYSEC-2026-40","url":"https://osv.dev/vulnerability/PYSEC-2026-40","license":"CC-BY-4.0","modified_at":"2026-05-20T09:18:56.669156Z","relation":"self"},{"provider":"redhat-vex","source_id":"CVE-2026-44513","url":"https://access.redhat.com/security/cve/CVE-2026-44513","license":"CC-BY-4.0","modified_at":"2026-08-10T11:00:52.758843Z","relation":"self"}]}
