Skip to main content
EPSS 1.6%top 26%

Red Hat Security Advisory: Red Hat AI Inference Server 3.2.5 (ROCm)

0
High
Published: 12/15/2025 (12/15/2025, 15:38:07 UTC)
Source: GCVE Database
Vendor/Project: Red Hat Product Security
Product: Red Hat

Description

Red Hat® AI Inference Server

Affected software

Affected versions
>=3.2.0 <=3.2.5Red HatRed Hat AI Inference ServerRed Hat AI Inference Server 3.2amd64registry.redhat.io/rhaiis/vllm-rocm-rhel9@sha256:e3b3efcdd86f60b90664a249d45918b2ac5f45bae5eed5399e310d63e878b287_amd64

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 08/14/2026, 22:19:00 UTC

Technical Analysis

This advisory covers multiple vulnerabilities affecting Red Hat AI Inference Server 3.2.0 through 3.2.5 (ROCm). Among these, CVE-2025-22868 is a flaw in the golang.org/x/oauth2/jws package's token parsing logic, where the use of strings.Split(token, ".") can cause excessive memory consumption and denial of service when processing tokens with many '.' characters. The advisory lists 11 CVEs in total, including CVE-2025-9230. Red Hat has not yet provided patches for these vulnerabilities. The vendor recommends mitigation by pre-validating tokens to prevent excessive '.' characters. The vulnerabilities have not been observed exploited in the wild. The advisory emphasizes that CVSS scores may vary by vendor and that Red Hat's severity rating is high for these issues.

Potential Impact

The primary impact is potential denial of service due to memory exhaustion when processing maliciously crafted tokens, as seen in CVE-2025-22868. Other vulnerabilities included in the advisory may have varying impacts, but no exploits are currently known in the wild. The high severity rating indicates significant risk if exploited, particularly affecting availability of the AI Inference Server.

Mitigation Recommendations

No official fix or patch is currently available for these vulnerabilities. Red Hat recommends pre-validating any payloads passed to the go-jose library to ensure they do not contain an excessive number of '.' characters, mitigating the risk of memory exhaustion and denial of service. Users should monitor Red Hat advisories for updates and patches. Applying this mitigation reduces risk until an official fix is released.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Gcve Source
db.gcve.eu
Csaf Category
csaf_security_advisory
Csaf Version
2.0
Publisher
Red Hat Product Security
Advisory Id
RHSA-2025:23205
Cve Count
11
Additional Cves
["CVE-2025-9714","CVE-2025-22868","CVE-2025-22869","CVE-2025-47906","CVE-2025-52565","CVE-2025-59375","CVE-2025-62164","CVE-2025-62372","CVE-2025-66448","CVE-2025-66506"]

Threat ID: 6a160974e29bf47b5063defb

Added to database: 05/26/2026, 20:58:28 UTC

Last enriched: 08/14/2026, 22:19:00 UTC

Last updated: 09/10/2026, 19:36:52 UTC

Views: 92

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Need more coverage?

Upgrade to Pro Console for AI refresh and higher limits.

For incident response and remediation, OffSeq services can help resolve threats faster.

Latest Threats

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses