CVE-2026-93989: vLLM bad_words token index validation flaw corrupts concurrent request logits

Summary

vLLM through 0.29.0 does not properly validate bad_words token indices against the model's generation output width in SamplingParams.update_from_tokenizer(). An attacker can supply out-of-bounds token indices that corrupt the logits memory of concurrent requests, so different in-flight HTTP requests return incorrect tokens.

Mitigation

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

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