{"id":"CVE-2026-93841","title":"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","summary":"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 multimoda…","severity":"low","cvss":3.7,"cvssVector":"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N","cwe":["CWE-129","CWE-787"],"vendor":"vllm","product":"vllm","affected":["vllm <= 0.29.0"],"published":"2026-09-18","updated":"2026-09-28","sourceUpdated":"2026-09-28T18:35:40.697","source":"NVD","sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2026-93841","references":[{"url":"https://github.com/vllm-project/vllm","label":"disclosure@vulncheck.com"},{"url":"https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/worker/gpu/sample/penalties.py#L241-L255","label":"disclosure@vulncheck.com"},{"url":"https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/worker/gpu/sample/penalties.py#L33-L37","label":"disclosure@vulncheck.com"},{"url":"https://github.com/vllm-project/vllm/pull/49081","label":"disclosure@vulncheck.com"},{"url":"https://www.vulncheck.com/advisories/vllm-through-0.29.0-adjacent-request-sampler-state-corruption-via-unvalidated-prompt-token-ids","label":"disclosure@vulncheck.com"},{"url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-93841.json"},{"url":"https://access.redhat.com/security/cve/CVE-2026-93841"},{"url":"https://bugzilla.redhat.com/show_bug.cgi?id=2539027"},{"url":"https://www.cve.org/CVERecord?id=CVE-2026-93841"},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-93841"}],"tags":["nvd","cve.org","csaf","vex","red-hat","osv","pip"],"ssvc":{"exploitation":"none","automatable":"no","technicalImpact":"partial","timestamp":"2026-09-21T16:22:54.286847Z"},"ingestedAt":"2026-09-18T19:49:30.603Z","epss":0.00237,"epssPercentile":0.14681,"aliases":["PYSEC-2026-3999"],"ecosystem":"pip","patched":["vllm 0.30.0"],"scores":{"nvd":3.7,"osv":5.3},"slug":"CVE-2026-93841","body":"## Overview\n\nvLLM 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.\n\n## Affected\n\n- `vllm <= 0.29.0`\n\n## Remediation\n\nRefer to the linked advisories for vendor-supplied fixes and affected version ranges.\n\n## Vendor advisories\n\n- **Red Hat VEX** · Low · affected: Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3, Red Hat OpenShift AI (RHOAI) · no fix planned: Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3, Red Hat OpenShift AI (RHOAI) · updated 2026-09-28 · [vex](https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-93841.json)\n\n## Package advisory (CVE-2026-93841)\n\nAffected packages:\n\n- `vllm < 0.30.0`\n\nPatched in:\n\n- `vllm 0.30.0`\n\nSource: https://osv.dev/vulnerability/PYSEC-2026-3999","depth":"sunlit","depthScore":20,"depthScoreParts":{"impact":20.4,"likelihood":0,"exploitation":0,"ransomware":0},"changes":[]}