RHSA-2026:57387HighCVSS 7.8

Red Hat Security Advisory: Red Hat AI Inference 3.4.4 (spyre)

Published
August 20, 2026
Last Modified
August 23, 2026

🔗 CVE IDs covered (10)

CVE-2026-44223 →CVE-2026-34755 →CVE-2026-34756 →CVE-2026-41523 →CVE-2026-42308 →CVE-2026-42310 →CVE-2026-42311 →CVE-2026-34753 →CVE-2026-40192 →CVE-2026-42309 →

📋 Description

CVE-2026-34753 — vllm: vLLM: Server-Side Request Forgery allows access to internal services via controlled batch input CVE-2026-34755 — vLLM: vLLM: Denial of Service due to excessive video frame processing CVE-2026-34756 — vllm: vLLM: Denial of Service via excessively large 'n' parameter in OpenAI-compatible API CVE-2026-40192 — Pillow: Pillow: Denial of Service via decompression bomb in FITS image processing CVE-2026-41523 — vllm: vLLM: Arbitrary code execution via malicious HuggingFace model CVE-2026-42308 — Pillow: python: Pillow: Denial of Service via integer overflow in font processing CVE-2026-42309 — Pillow: Pillow: Denial of Service via specially crafted coordinate input CVE-2026-42310 — Pillow: Pillow: Denial of Service via malicious PDF processing CVE-2026-42311 — Pillow: python-pillow: Pillow: Arbitrary code execution via malicious PSD file processing CVE-2026-44223 — vllm: vLLM: Denial of Service via malformed tensor shape in speculative decoding

🎯 Affected products4

  • Red Hat AI Inference Server 3.4
  • registry.redhat.io/rhaii/vllm-spyre-rhel9@sha256:3657354eb0edeb7e0e9aad2a434d7f264626b3d906f4e3e8502a95a73772ca41_s390x as a component of Red Hat AI Inference Server 3.4
  • registry.redhat.io/rhaii/vllm-spyre-rhel9@sha256:54ad323a1a44f99991ca9d28cf0a364a44c5bbce143891936f6c668612c3ffb0_amd64 as a component of Red Hat AI Inference Server 3.4
  • registry.redhat.io/rhaii/vllm-spyre-rhel9@sha256:b35ecb302c7f4e270f44bf70b7f7f8d053eb74761b1104fea346af9a8e089d09_ppc64le as a component of Red Hat AI Inference Server 3.4

✅ Remediation

For more information visit https://access.redhat.com/errata/RHSA-2026:57387 Workaround: Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base or stability. Workaround: Avoid running vLLM with python -O or PYTHONOPTIMIZE=1 until updated packages are available. Only load models from trusted sources. Restrict who can deploy or update models on inference endpoints. Apply network access controls and authentication in front of vLLM APIs. Workaround: To mitigate this issue, ensure that applications utilizing the Pillow library do not process untrusted or maliciously crafted font files. Additionally, consider running applications that process image data in a sandboxed environment to limit potential impact. Reloading or restarting affected services may be required for changes to take effect. Workaround: To mitigate this vulnerability, users should avoid processing untrusted or suspicious PSD image files with applications that utilize the Pillow library. Implementing strict input validation and sanitization for image uploads and processing workflows can reduce the risk. Additionally, running applications that process untrusted content within a sandboxed environment can limit the potential impact of successful exploitation. Workaround: Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base, or stability.

🔗 References (14)