Skip to content
Fencer Vulns
critical 9.9

CVE-2026-18948 json

Feast: feast: unsafe dill deserialization of registry-stored udfs — rce on feature server and registry server

published 2026-08-10 2 mo ago modified 2026-11-03 5 d ago also GHSA-gg2p-37pv-v7fq , EUVD-2026-55818

cvss
9.9
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
1.1%
EPSS 1.1% chance of exploitation in 30 days, percentile 65%
public exploits
0
none known

Summary

A flaw was found in Feast. The system improperly deserializes user-defined functions (UDFs) stored in its registry, which are serialized using the 'dill' library. This allows a remote attacker to store a malicious UDF, leading to unauthenticated arbitrary code execution on the feature server in default configurations. An authenticated attacker can also achieve arbitrary code execution on the registry server by bypassing authorization checks during deserialization. This vulnerability can result in cross-tenant data access and lateral movement within the system.

Patch / fix

  • pypi feast 0.67.0
  • Red Hat Red Hat OpenShift AI 2.25 1786110051
  • Red Hat Red Hat OpenShift AI 3.3 1786110033
  • Red Hat Red Hat OpenShift AI 3.4 1786107278, 1787068065

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-2026-18948 updated cvss 9.9

feast: Feast: Unsafe dill deserialization of registry-stored UDFs — RCE on feature server and registry server

  • Red Hat OpenShift AI 2.25 rhoai/odh-feature-server-rhel9 1786110051
    fixed: vendor fix RHSA-2026:53261
  • Red Hat OpenShift AI 3.3 rhoai/odh-feature-server-rhel9 1786110033
    fixed: vendor fix RHSA-2026:53263
  • Red Hat OpenShift AI 3.4 rhoai/odh-feature-server-rhel9 1786107278, rhoai/odh-feature-server-rhel9 1787068065
    fixed: vendor fix RHSA-2026:53262
  • Red Hat OpenShift AI (RHOAI) rhoai/odh-pipeline-runtime-pytorch-cuda-py312-rhel9, rhoai/odh-pipeline-runtime-pytorch-rocm-py312-rhel9, rhoai/odh-workbench-jupyter-pytorch-cuda-py312-rhel9, rhoai/odh-workbench-jupyter-pytorch-rocm-py312-rhel9, rhoai/odh-pipeline-runtime-datascience-cpu-py312-rhel9, rhoai/odh-pipeline-runtime-tensorflow-cuda-py312-rhel9, +7 more Red Hat OpenShift AI 2.25 rhoai/odh-rhel9-operator 1786112809, rhoai/odh-dashboard-rhel9 1785940823, rhoai/odh-operator-bundle 1786113363, rhoai/odh-caikit-nlp-rhel9 1785186995, rhoai/odh-ta-lmes-job-rhel9 1785187011, rhoai/odh-feast-operator-rhel9 1786110116, +19 more Red Hat OpenShift AI 3.3 rhoai/odh-trainer-rhel9 1785187865, rhoai/odh-rhel9-operator 1786129846, rhoai/odh-dashboard-rhel9 1786109683, rhoai/odh-operator-bundle 1786130475, rhoai/odh-ta-lmes-job-rhel9 1785187607, rhoai/odh-mod-arch-maas-rhel9 1786109736, +21 more Red Hat OpenShift AI 3.4 rhoai/odh-cli-rhel9 1787330837, rhoai/rhai-cli-rhel9 1787330837, rhoai/odh-automl-rhel9 1786612415, rhoai/odh-mlflow-rhel9 1787226790, rhoai/odh-autorag-rhel9 1786612637, rhoai/odh-trainer-rhel9 1784039162, +135 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
none
Automatable
no
Technical impact
total
Assessed
2 mo ago

Exploit prediction

1.08% chance of exploitation in the next 30 days, higher than 65% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by version score vector
CNA 3.1 9.9 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
GitHub 3.1 9.9 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H

Affected packages

ecosystem package affected fixed in
pypi feast
<0.67.0
0.67.0

Affected products

  • Red Hat Red Hat OpenShift AI 2.25
  • Red Hat Red Hat OpenShift AI 3.3
  • Red Hat Red Hat OpenShift AI 3.4
  • Red Hat Red Hat OpenShift AI (RHOAI)

Classification

Weakness
  • CWE-502 Deserialization of Untrusted Data

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.