CVE-2026-93592High· 7.5▾ MidnightPoC availablevLLM versions before 0.28.0 fail to validate the lower bound of token IDs in the /v1/embeddings and /pooling endpoints, allowing unauthenticated attackers to crash the engine by submitting negative token IDs. A single request with a nega…
▾ Midnight zone — Critical, or high with PoC / in-the-wild
impact 41.3 · likelihood 0.1 · exploitation 12
A public proof-of-concept already exists for this vulnerability — see Exploit availability below.
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
Exploit / PoC code exists
0.4%
Last analysed / modified upstream
vLLM versions before 0.28.0 fail to validate the lower bound of token IDs in the /v1/embeddings and /pooling endpoints, allowing unauthenticated attackers to crash the engine by submitting negative token IDs. A single request with a negative token ID triggers a CUDA device-side assertion that poisons the GPU context, causing all subsequent requests to fail until the process restarts.
Refer to the linked advisories for vendor-supplied fixes and affected version ranges.
Field changes observed since this record was first indexed.
Connected 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-2026-93841Low· 3.7vLLM 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
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-2026-69147Medium· 6.5vLLM is an inference and serving engine for large language models
CVE-2026-90878Medium· 4.3A vulnerability was determined in vllm-project vLLM up to 0.27.1
CVE-2026-90713Low· 3.3A security flaw has been discovered in vllm-project vLLM up to 0.29.0