Skip to content
Fencer Vulns
high 8.8

CVE-2026-57516 json

Ray < 2.56.0 Unsafe Deserialization RCE via WebDataset Reader

published 2026-07-01 4 mo ago modified 2026-11-08 26 h ago also EUVD-2026-41089 , GHSA-hhrp-gw25-jr43 , PYSEC-2026-2273

cvss
8.8
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.9%
EPSS 0.9% chance of exploitation in 30 days, percentile 58%
public exploits
0
none known

Summary

Ray prior to 2.56.0 contains an unsafe deserialization vulnerability in the WebDataset reader that allows attackers to achieve remote code execution by supplying a malicious tar archive to the read_webdataset() function. The _default_decoder() function in webdataset_datasource.py unconditionally calls pickle.loads() on tar entries with .pkl/.pickle extensions and torch.load() with weights_only=False on .pt/.pth entries, executing arbitrary code inside Ray remote workers on every worker that processes the malicious archive.

Patch / fix

  • pypi ray 2.56.0
  • Anyscale, Inc Ray 2.56.0

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2026-57516 updated cvss 8.8

ray: Ray: Remote code execution via unsafe deserialization in WebDataset reader

  • Red Hat AI Inference Server rhaii/vllm-gaudi-rhel9 Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-gaudi-rhel9
    affected: workaround, no fix planned “Will not fix”
  • Red Hat AI Inference Server 3.2 rhaiis/vllm-cuda-rhel9 1787860580
    fixed: vendor fix RHSA-2026:61627
  • Red Hat AI Inference Server 3.3 rhaiis/vllm-cuda-rhel9 1789582776
    fixed: vendor fix RHSA-2026:68699
  • Red Hat Enterprise Linux AI 3.3 rhelai3/bootc-cuda-rhel9 1790866732, rhelai3/bootc-aws-cuda-rhel9 1790936334, rhelai3/bootc-gcp-cuda-rhel9 1790936334, rhelai3/disk-image-cuda-rhel9 1790954179, rhelai3/bootc-azure-cuda-rhel9 1790936351
    fixed: vendor fix RHSA-2026:76041
  • Red Hat OpenShift AI 3.4 rhoai/odh-pipeline-runtime-pytorch-cuda-py312-rhel9 1792721112, rhoai/odh-pipeline-runtime-pytorch-rocm-py312-rhel9 1792721018, rhoai/odh-workbench-jupyter-pytorch-cuda-py312-rhel9 1792721192, rhoai/odh-workbench-jupyter-pytorch-rocm-py312-rhel9 1792722164, rhoai/odh-workbench-jupyter-trustyai-cpu-py312-rhel9 1792721192, rhoai/odh-pipeline-runtime-datascience-cpu-py312-rhel9 1792721265, +6 more
    fixed: vendor fix RHSA-2026:92510
  • Red Hat Enterprise Linux AI 3.3 rhelai3/bootc-rocm-rhel9 1790791893, rhelai3/bootc-azure-rocm-rhel9 1790850900 Red Hat OpenShift AI (RHOAI) rhoai/odh-vllm-gaudi-rhel9, rhoai/odh-kserve-agent-rhel9, rhoai/odh-kserve-router-rhel9, rhoai/odh-kserve-controller-rhel9, rhoai/odh-kserve-storage-initializer-rhel9 Red Hat OpenShift AI 3.4 rhoai/odh-cli-rhel9 1792722177, rhoai/rhai-cli-rhel9 1792722177, rhoai/odh-automl-rhel9 1792697253, rhoai/odh-mlflow-rhel9 1793002327, rhoai/odh-autorag-rhel9 1793265800, rhoai/odh-trainer-rhel9 1792817113, +88 more
    not affected: vulnerable code not present

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
Proof of concept is public
Automatable
no
Technical impact
total
Assessed
4 mo ago

Exploit prediction

0.86% chance of exploitation in the next 30 days, higher than 58% of all scored CVEs (FIRST EPSS, 2026-11-08).

Exploits and checks

  • github.com https://github.com/ray-project/ray/security/advisories/GHSA-hhrp-gw25-jr43 referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 4.0 8.6 CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
CNA 3.1 8.8 CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
GitHub 3.1 8.8 CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
CNA 4.0 8.6 CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Affected packages

ecosystem package affected fixed in
pypi ray
<2.56.0
2.56.0

Affected products

  • Anyscale, Inc Ray

Classification

Weakness
  • CWE-502 Deserialization of Untrusted Data
  • CWE-94 Improper Control of Generation of Code

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.