Read the docs
TI-2026-32443 Aliases CVE-2026-44513GHSA-98h9-4798-4q5v

Diffusers: `trust_remote_code` bypass via `custom_pipeline` and local custom components

Priority MEDIUM 42CWE-94Published · Updated

Key facts

Attack vector
Network
Privileges required
None
User interaction
Required
Attack complexity
Low
Impact type
Code execution
Confidentiality · integrity · availability
High · High · High
Fix status
Partial Red Hat: 3 fixed, 2 without a fix

Attack profile from CVSS 3.1 · CNA. Fix status from CNA, GitHub and Red Hat. Impact type from CWE-94.

Summary

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.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.01071 65th percentileScored 2026-11-07
Public exploit Yes 1 exploit referenceTagged by NVD
Fix Partial diffusers (huggingface): 0.38.0diffusers (PyPI): 0.38.0Red Hat: 7 advisoriesRed Hat: 3 fixed, 2 without a fix

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
None
Automatable
No
Technical impact
Total

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

VendorProductAffected versionsFixed inStatusSource
huggingfacediffusersbefore 0.38.00.38.0Patch availableCNA
—diffusers (PyPI)before 0.38.00.38.0Patch availableGHSA-98h9-4798-4q5v
  • diffusers Vendorhuggingface Affected before 0.38.0 Fixed in 0.38.0 Patch available CNA
  • diffusers (PyPI) Vendor— Affected before 0.38.0 Fixed in 0.38.0 Patch available GHSA-98h9-4798-4q5v

CPE configurations NVD · 1

CPEVersionsRoleVendor
cpe:2.3:a:huggingface:diffusers:*:*:*:*:*:python:*:*before 0.38.0Vulnerablehuggingface
  • cpe:2.3:a:huggingface:diffusers:*:*:*:*:*:python:*:* Versions before 0.38.0 Vulnerable ·huggingface

Remediation

  • Fix · CNA diffusers (huggingface) Fixed in 0.38.0
  • Fix · GHSA-98h9-4798-4q5v diffusers (PyPI) Fixed in 0.38.0 Advisory →

Red Hat 7 advisories

  • RHSA-2026:76150 Released 2026-10-05 · Red Hat rating Important
    Red Hat Enterprise Linux AI 3.4.5 security update
    • Red Hat Enterprise Linux AI 3.4 registry.redhat.io/rhelai3/bootc-aws-cuda-rhel9, registry.redhat.io/rhelai3/bootc-azure-cuda-rhel9, registry.redhat.io/rhelai3/bootc-azure-rocm-rhel9 +3
  • RHSA-2026:76149 Released 2026-10-05 · Red Hat rating Important
    Red Hat Enterprise Linux AI 3.4.5 security update
    • Red Hat Enterprise Linux AI 3.4 registry.redhat.io/rhelai3/disk-image-cuda-rhel9
  • RHSA-2026:70979 Released 2026-09-23 · Red Hat rating Important
    Red Hat AI Inference 3.4.5 (cuda)
    • Red Hat AI Inference Server 3.4 registry.redhat.io/rhaii/vllm-cuda-rhel9
Show 4 more Red Hat advisories
  • RHSA-2026:70965 Released 2026-09-23 · Red Hat rating Important
    Red Hat AI Inference 3.4.5 (cpu)
    • Red Hat AI Inference Server 3.4 registry.redhat.io/rhaii/vllm-cpu-rhel9
  • RHSA-2026:69467 Released 2026-09-21 · Red Hat rating Important
    Red Hat AI Inference 3.4.5 (cuda)
    • Red Hat AI Inference Server 3.4 registry.redhat.io/rhaii/vllm-cuda-rhel9
  • RHSA-2026:69466 Released 2026-09-21 · Red Hat rating Important
    Red Hat AI Inference 3.4.5 (cpu)
    • Red Hat AI Inference Server 3.4 registry.redhat.io/rhaii/vllm-cpu-rhel9
  • RHSA-2026:60520 Released 2026-08-27 · Red Hat rating Critical
    RHOAI 3.4.4 - Red Hat OpenShift AI
    • Red Hat OpenShift AI 3.4 registry.redhat.io/rhoai/odh-automl-rhel9, registry.redhat.io/rhoai/odh-autorag-rhel9, registry.redhat.io/rhoai/odh-built-in-detector-rhel9 +47

Vendor assessments

Red Hat

Red Hat rating: Important. Red Hat's page for this CVE →

ProductStatusPlan or fix
Red Hat AI Inference ServerAffectedNo fix planned: Will not fix
Red Hat OpenShift AI (RHOAI)AffectedNo fix yet
Red Hat AI Inference Server 3.4Fixed RHSA-2026:69466, RHSA-2026:69467, RHSA-2026:70965, RHSA-2026:70979
Red Hat Enterprise Linux AI 3.4Fixed RHSA-2026:76149, RHSA-2026:76150
Red Hat OpenShift AI 3.4Fixed RHSA-2026:60520
Not affected: 4 products
  • Red Hat AI Inference Server
  • Red Hat Enterprise Linux AI 3.4
  • Red Hat OpenShift AI (RHOAI)
  • Red Hat OpenShift AI 3.4

Timeline

  1. 2026-10-02 Threatist record created from CVE-2026-44513
  2. 2026-10-03 Alias added: GHSA-98h9-4798-4q5v
  3. 2026-10-06 Fix available: RHSA-2026:76149 · Red Hat
  4. 2026-10-06 Fix available: RHSA-2026:76150 · Red Hat
  5. 2026-10-06 Fix available: Red Hat Enterprise Linux AI 3.4 · Red Hat

References

  • TI-2026-32710 Diffusers: None.py Trust Remote Code Bypass CVSS 3.1HIGH 8.8
  • TI-2026-33539 Diffusers: TOCTOU Trust Remote Code Bypass CVSS 3.1HIGH 7.5

Sources