CVE Tools

CVE-2026-44513

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

No known exploitation. EPSS puts it in the 58th percentile. Only a workaround so far.

Published Updated Sources: CVE.org, NVD

What to do

No fixed build is published yet. The vendor describes a workaround.

What it is

From the CVE record

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.

In plain language

No plain-language summary for this CVE yet.

Exploitation

Where each signal puts this CVE on the scale from published to confirmed exploited.

EPSS58th
CISA KEV

Not in the catalog. CISA has not confirmed exploitation.

Public exploits

No public exploit or proof of concept found in the sources we track.

EPSS

0.9% chance of exploitation activity in the next 30 days, which ranks it in the 58th percentile of scored CVEs.

Exploit Prediction Scoring System, FIRST.org. A probability, not a confirmation.

Lifecycle

9 events over 106 days, from the signal feeds we watch.

  1. Workaround availablerecord updated
  2. Workaround availablerecord updated
  3. Workaround availablerecord updated
  4. Publishedweakness classified, att&ck mapped

Affected products

Technical detail

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

Scored 8.8 by NVD.

How it is reached

  • Attack Vector NetworkExploitable remotely over the network without any special conditions
  • Attack Complexity LowNo special conditions — the attack can be reliably reproduced
  • Privileges Required NoneNo authentication required — anyone can exploit this
  • User Interaction RequiredA user must click a link, open a file, or perform some action

Scope

  • Scope UnchangedImpact is limited to the vulnerable component itself

Impact if exploited

  • Confidentiality HighTotal information disclosure — all data in the component is compromised
  • Integrity HighTotal loss of integrity — attacker can modify any data in the component
  • Availability HighTotal denial of service — the component is completely unavailable

Weaknesses

ATT&CK techniques

Mapped from the weaknesses above (CWE to ATT&CK), not observed in attacks.

Sources

Watch the software you run.

My Stack ranks new CVEs for your products by real-world exploitation, so the next serious one reaches you without reading every advisory.

We'll flag the next CVE, public exploit or patch for Diffusers, not every advisory.

We use analytics cookies to see which pages and articles actually help people. Decline and none of them run — the site works the same. What we store