Read the docs
TI-2026-78542 Aliases CVE-2026-17557GHSA-xphj-jg67-vf2w

lm-evaluation SSRF via JobSpec model.url forwards bearer credentials

Priority LOW 29CWE-918Published · Updated

Key facts

Attack vector
Network
Privileges required
Low
User interaction
None
Attack complexity
Low
Impact type
Information disclosure
Confidentiality · integrity · availability
High · None · None
Fix status
Deferred Red Hat: fix deferred

Attack profile from CVSS 3.1 · CNA. Fix status from CNA and Red Hat. Impact type from CWE-918 and the CVSS impact.

Summary

A flaw in the lm-evaluation component of Red Hat OpenShift AI lets an authenticated user who can submit an evaluation job supply a malicious model URL in the JobSpec. The attacker can receive the tenant's model authentication secret at an external listener under their control. The same flaw enables Server-Side Request Forgery (CWE-918) against internal network endpoints reachable from the evaluation job pod. The CVSS 3.1 base score is 6.5 (MEDIUM), and Red Hat rates the flaw Moderate.

Written with Claude Haiku 5.5 from the sources below · 2026-10-28

Description from the CNA

A flaw was found in the `lm-evaluation-harness` component of Red Hat OpenShift AI. An authenticated user, able to submit an evaluation job, could exploit this by providing a malicious model URL in the `JobSpec`. This vulnerability allows for the disclosure of the tenant's model authentication secret to an attacker-controlled external listener. Additionally, it enables Server-Side Request Forgery (SSRF) attacks against internal network endpoints reachable from the evaluation job pod.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.00327 25th percentileScored 2026-11-07
Fix Deferred Red Hat: fix deferred

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
None
Automatable
No
Technical impact
Partial

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

Affected products

VendorProductAffected versionsFixed inStatusSource
Red HatRed Hat OpenShift AI (RHOAI)——No fix listedCNA
  • Red Hat OpenShift AI (RHOAI) VendorRed Hat Affected — Fixed in — No fix listed CNA

CPE names CNA · 1

CPEVersionsRoleVendor
cpe:/a:redhat:openshift_ai——Red Hat
  • cpe:/a:redhat:openshift_ai Versions — — ·Red Hat

Remediation

The sources list no fixed version for Red Hat OpenShift AI (RHOAI), and no plan is available. Until a fix ships, limit evaluation job submission to trusted users, since exploitation requires an authenticated user who can submit a job.

Written with Claude Haiku 5.5 from the sources below · 2026-10-28

Vendor assessments

Red Hat

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

ProductStatusPlan or fix
Red Hat OpenShift AI (RHOAI)AffectedNo fix yet: Fix deferred

Timeline

  1. 2026-10-21 Threatist record created from CVE-2026-17557
  2. 2026-10-21 Affected versions changed · Red Hat
  3. 2026-10-21 CVSS score added · Red Hat
  4. 2026-10-21 Alias added: GHSA-xphj-jg67-vf2w
  5. 2026-10-21 CISA SSVC decision points changed
  6. 2026-10-21 Priority changed: MEDIUM → LOW

References

Other 2

  • TI-2019-15875 Protection mechanism failure in Jenkins Pipeline: Groovy Plugin KEVCVSS 3.1CRITICAL 9.9
  • TI-2019-15874 Protection mechanism failure in Jenkins Script Security Plugin KEVCVSS 3.1CRITICAL 9.9
  • TI-2019-08259 Underflow in PHP-FPM can lead to RCE KEVCVSS 3.1CRITICAL 9.8
  • TI-2019-05363 Code injection in Elastic Kibana KEVCVSS 3.1CRITICAL 10.0
  • TI-2019-03949 Out-of-bounds write in ESXi and Horizon DaaS KEVCVSS 3.1CRITICAL 9.8
  • TI-2018-16080 A code execution vulnerability exists in the Stapler web framework used by Jenkins 2.153… KEVCVSS 3.1CRITICAL 9.8
See all 7413 →

Sources

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences