CVE-2026-5497: vLLM out-of-memory denial of service via unbounded video frames in data URLs

Summary

vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory denial of service through the `VideoMediaIO.load_base64()` method. When processing `video/jpeg` data URLs, the method splits the base64 string on commas without enforcing a frame count limit. A single request to the OpenAI-compatible chat completions API containing thousands of frames can exhaust server memory and crash it, and no authentication is required.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Affected packages in the Exposure Registry

Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.

• vllmPyPILLM dependency since 2023-08-25 · 15 tracked dependents

Topics

• Inference infrastructure

Related items

• LowCloakFEM: Agentic FEM Code Generation for Red-Teaming Computational Resource ExhaustionSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• MediumThe Rise of LLMJacking: How Threat Actors Monetize Compromised Cloud and Model ResourcesSimilar attack · Google Threat Intelligence
• InfoThe Blind Spots of Detection: Adversarial Perturbation Attacks against Watchdogs in Distributed LLM InferenceSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• HighCVE-2026-118761: Kubeflow Pipelines decompression bomb in pipeline archive uploadSimilar attack · NVD/CVE Database
• LowOpenCode User Hit with Hostile Backlash After Reporting Free AI LoopholeSimilar attack · Socket Blog