Technology · Red Hat
Red Hat AI Inference Server vulnerabilities
Updated . Rebuilt every hour.
Junglewise Threat Intelligence has tracked 16 vulnerabilities in Red Hat AI Inference Server: 0 in the last 7 days and 0 in the last 90 days, 0 of them critical and 0 exploited in the wild. The most recent, vLLM improper image metadata normalization in image processing, was published on 17 June 2026.
- Last 7 days
- 0
- Last 90 days
- 0
- Critical, all time
- 0
- Exploited in the wild
- 0
About Red Hat AI Inference Server
A Red Hat software component designed to serve machine learning models for inference tasks.
Latest Red Hat AI Inference Server vulnerabilities
- vLLM improper image metadata normalization in image processingmediumCVSS 4.8
- CVE-2026-12491: vLLM improper image metadata handling in image processingmediumCVSS 4.8EPSS 0.2%
- CVE-2026-42561: Kludex python-multipart denial of service in multipart header parsinghighCVSS 7.5EPSS 0.9%
- CVE-2026-41603: Apache Thrift improper certificate validation in Java TSSLTransportFactoryhighCVSS 7.4EPSS 0.3%
- CVE-2026-41602: Apache Thrift integer overflow in Go TFramedTransporthighCVSS 7.5EPSS 1.4%
- CVE-2026-34756: vLLM Denial of Service via unbounded n parameter in OpenAI API servermediumCVSS 6.5EPSS 0.8%
- CVE-2026-34755: vLLM denial of service via unbounded video frame processingmediumCVSS 6.5EPSS 0.8%
- CVE-2026-27893: vLLM remote code execution via hardcoded remote code trust in modelshighCVSS 8.8EPSS 1.8%
- CVE-2026-32981: Anyscale Ray path traversal in Ray DashboardhighCVSS 7.5EPSS 1.0%
- CVE-2026-28356: defnull multipart ReDoS in parse_options_headerhighCVSS 7.5EPSS 1.0%
- CVE-2026-23868: Giflib double free in GifMakeSavedImagemediumCVSS 5.1EPSS 0.1%
- CVE-2026-25048: mlc-ai xgrammar uncontrolled recursion in nested syntaxhighCVSS 7.5EPSS 0.7%
- CVE-2025-14831: GnuTLS denial of service via excessive resource consumption during certificate verificationmediumCVSS 5.3EPSS 0.1%
- CVE-2026-24779: vLLM SSRF in MediaConnector via URL parsing discrepancyhighCVSS 7.1EPSS 0.6%
- CVE-2026-1260: Google Sentencepiece heap overflow via malicious model filehighCVSS 7.8EPSS 0.2%
- CVE-2026-22807: vLLM arbitrary code execution via auto_map dynamic module loadinghighCVSS 8.8EPSS 0.8%
Most severe Red Hat AI Inference Server vulnerabilities
Exploited in the wild first, then by severity and CVSS score.
- CVE-2026-27893: vLLM remote code execution via hardcoded remote code trust in modelshighCVSS 8.8EPSS 1.8%
- CVE-2026-22807: vLLM arbitrary code execution via auto_map dynamic module loadinghighCVSS 8.8EPSS 0.8%
- CVE-2026-1260: Google Sentencepiece heap overflow via malicious model filehighCVSS 7.8EPSS 0.2%
- CVE-2026-41602: Apache Thrift integer overflow in Go TFramedTransporthighCVSS 7.5EPSS 1.4%
- CVE-2026-32981: Anyscale Ray path traversal in Ray DashboardhighCVSS 7.5EPSS 1.0%
- CVE-2026-28356: defnull multipart ReDoS in parse_options_headerhighCVSS 7.5EPSS 1.0%
- CVE-2026-42561: Kludex python-multipart denial of service in multipart header parsinghighCVSS 7.5EPSS 0.9%
- CVE-2026-25048: mlc-ai xgrammar uncontrolled recursion in nested syntaxhighCVSS 7.5EPSS 0.7%
- CVE-2026-41603: Apache Thrift improper certificate validation in Java TSSLTransportFactoryhighCVSS 7.4EPSS 0.3%
- CVE-2026-24779: vLLM SSRF in MediaConnector via URL parsing discrepancyhighCVSS 7.1EPSS 0.6%
Vulnerabilities per week
The last 13 weeks, by the week each vulnerability was published.
| Week of | Bar | Vulns | Critical |
|---|---|---|---|
| 29 Jun 2026 | 0 | 0 | |
| 6 Jul 2026 | 0 | 0 | |
| 13 Jul 2026 | 0 | 0 | |
| 20 Jul 2026 | 0 | 0 | |
| 27 Jul 2026 | 0 | 0 | |
| 3 Aug 2026 | 0 | 0 | |
| 10 Aug 2026 | 0 | 0 | |
| 17 Aug 2026 | 0 | 0 | |
| 24 Aug 2026 | 0 | 0 | |
| 31 Aug 2026 | 0 | 0 | |
| 7 Sep 2026 | 0 | 0 | |
| 14 Sep 2026 | 0 | 0 | |
| 21 Sep 2026 | 0 | 0 |
How this is built
Junglewise Threat Intelligence collects vulnerabilities from NVD, GitHub Security Advisories, OSV, the CISA Known Exploited Vulnerabilities catalog, FIRST EPSS and vendor advisories, and matches each one to the technologies and vendors it affects. Dates are the date a vulnerability was published, in UTC.
The pages are rebuilt from the database every hour. Frozen weekly and monthly reports never change once published, so they can be cited.
Use this data
The same data is at https://junglewise.ai/threats/technologies/ai-inference-server.json, for scripts and language models. It is free to reuse under CC BY 4.0 with a link back to this page.
Cite as: Junglewise Threat Intelligence, "Red Hat AI Inference Server vulnerabilities", https://junglewise.ai/threats/technologies/ai-inference-server, 26 September 2026.