What’s Vulnerable › Vulnerabilities

CVE-2026-93841: vLLM through 0.29.0 Adjacent-Request Sampler State Corruption via Unvalidated Prompt Token IDs

• Severity: medium (CVSS 5.3 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.2% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-09-18 · updated 2026-09-28
• Weakness: CWE-129

Description

vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton _bincount_kernel where prompt token IDs index the penalty prompt-presence bitset without bounds checking against vocabulary size. Attackers can submit multimodal audio requests with tokens equal to vocabulary size, causing out-of-bounds writes that corrupt concurrent requests' sampler state and alter repetition penalty behavior.

Affected products

• vllm-project vllm: through 0.29.0

References

• https://github.com/vllm-project/vllm
• https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/worker/gpu/sample/penalties.py#L241-L255
• https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/worker/gpu/sample/penalties.py#L33-L37
• https://github.com/vllm-project/vllm/pull/49081
• https://www.vulncheck.com/advisories/vllm-through-0.29.0-adjacent-request-sampler-state-corruption-via-unvalidated-prompt-token-ids

Get alerted when CVE-2026-93841 or the next vulnerability affects your stack