CVE-2025-29770: vLLM unbounded filesystem cache growth via outlines guided decoding

Summary

CVE-2025-29770 affects vLLM's structured output path, which uses the outlines library's on-disk grammar cache, on by default. The unconditional use of that cache in vllm/model_executor/guided_decoding/outlines_logits_processors.py lets a user send many short requests with unique schemas, each adding a cache entry. Because outlines is also reachable per request through the OpenAI-compatible API server, this can exhaust filesystem space and cause a Denial of Service. The issue applies only to the V0 engine.

Mitigation

Fixed in 0.8.0.

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