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.
Attack Parameters
Attack Vector
Network
Can be exploited remotely
Attack Complexity
Low
Easy to exploit
Attack Requirements
Present
Additional conditions required
Privileges Required
None
No privileges needed
User Interaction
None
No user interaction needed
Impact Assessment
Confidentiality
None
No data leak
Integrity
Low
Partial data modification
Availability
None
No disruption
CVSS Vector v4.0
Weakness Type (CWE)
References 5
https://github.com/vllm-project/vllm
disclosure@vulncheck.com
https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/worker/gpu/sample/pen…
disclosure@vulncheck.com
https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/worker/gpu/sample/pen…
disclosure@vulncheck.com
https://github.com/vllm-project/vllm/pull/49081
disclosure@vulncheck.com
https://www.vulncheck.com/advisories/vllm-through-0.29.0-adjacent-request-sampl…
disclosure@vulncheck.com