CVE-2026-93841Low· 3.7▾ SunlitvLLM 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 multimoda…
▾ Sunlit zone — Low / medium · no exploitation signal
impact 20.4 · likelihood 0 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
Stakeholder-Specific Vulnerability Categorization from CISA's ADP record at CVE.org: whether exploitation is observed, whether an attack can be automated, and how much of the system is at stake.
Exploit-prediction probability, daily snapshots since Sep 19.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via NVD
0.2%
0.2% → 0.4%
Last analysed / modified upstream
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.
vllm <= 0.29.0Refer to the linked advisories for vendor-supplied fixes and affected version ranges.
Affected packages:
vllm < 0.30.0Patched in:
vllm 0.30.0Connected by shared product, vendor, weakness, or advisory.
CVE-2026-93989Low· 3.1vLLM through 0.29.0 fails to properly validate bad_words token indices against the model's generation output width in SamplingParams.update_from_tokenizer()
CVE-2026-93840Low· 3.7vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width in SamplingParams._validate_allowed_token_ids()
CVE-2026-114050Medium· 6.5vLLM: Forged multimodal UUID + P0/P1 processor-cache eviction drift: unauthenticated remote crash of the whole vLLM engine
CVE-2026-114055High· 7.5vLLM 0.7.3 before 0.31.0 DoS via Unvalidated mm_processor_kwargs
CVE-2026-105760Medium· 5.3vLLM is an inference and serving engine for large language models
CVE-2026-105757Medium· 6.5vLLM is an inference and serving engine for large language models