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.
CVE-2026-93841
This low-severity CVE scores 3.7 under a secondary CVSS source (NVD's own analysis pending). EPSS exploit-prediction score not yet available (the EPSS model rescores nightly; freshly-published CVEs typically appear within 48 hours). GitHub Security Advisory data not yet ingested — confidence will rise once GHSA publishes (typical lag: hours to days for open-source ecosystem CVEs; never for infrastructure-only CVEs).
- Lower severity and no public exploit yet
No vendor fix yet — apply a workaround or compensating control (WAF / firewall / segmentation) and watch for a patch.
- CVSS v3
- 3.7
- EG Score
- 3.7(low)
- EG Risk
- 21(Track)EG Risk 21/100SSVC: Track
EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).
How it’s computedSeverity37% × 45%Exploitation0% × 40%Automatability30% × 15%Action: Routine — remediate on your standard cadence. - EPSS PROB
- —
- EPSS %ILE
- —
- KEV
- Not listed
Published
September 18, 2026
Last Modified
September 18, 2026
References (5)
- disclosure@vulncheckhttps://github.com/vllm-project/vllm
- disclosure@vulncheckhttps://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/worker/gpu/sample/penalties.py#L241-L255
- disclosure@vulncheckhttps://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/worker/gpu/sample/penalties.py#L33-L37
- disclosure@vulncheckhttps://github.com/vllm-project/vllm/pull/49081
- disclosure@vulncheckhttps://www.vulncheck.com/advisories/vllm-through-0.29.0-adjacent-request-sampler-state-corruption-via-unvalidated-prompt-token-ids
Vendor Advisories for CVE-2026-93841(1)
These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.
Weakness Classification(1)
MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.
Data Freshness Timeline
(refreshed 3× in last 7d / 3× in last 30d)
Each row is a source pipeline that fetched or updated this CVE on that date, with what changed. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. Most recent first.
- 2026-09-18 20:31 UTCEG score recompute
- 2026-09-18 19:19 UTCEG score recompute
- 2026-09-18 19:19 UTCMITRE cvelistV5first tracked
Frequently asked(4)
What is CVE-2026-93841?
When was CVE-2026-93841 disclosed?
What is the CVSS score of CVE-2026-93841?
How do I remediate CVE-2026-93841?
Dependency Blast Radius
Explore the affected products and dependency analysis for CVE-2026-93841
Is Your Infrastructure Affected by CVE-2026-93841?
EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.