CVE-2026-100652
What it is
vLLM versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with min_tokens greater than zero and out-of-vocabulary stop_token_ids to trigger CUDA tensor indexing failures that leave EngineCore in a fatal state requiring service restart.
At a glance
- Exploitability
- Can be exploited over the network without logging in. High risk of service disruption.
- Exploit odds
- 0.4% chance of exploitation in the next 30 days (EPSS).
- Fix
- A patch, advisory or fixed version is referenced. Upgrade or apply it.
Timeline
- PublishedDisclosed publicly on CVE.org and NVD
- Last updatedMost recent change to the record
Details
- Published
- Last modified
- Exploit probability
- 0.4% · EPSS, next 30 days
- Weakness
- CWE-20 · Improper input validation
- Record status
- Analyzed
Affected
- Vllm < 0.24.0
Attack profile CVSS 4.0 · 8.2
- Attack vector
- Network
- Complexity
- High
- Attack requirements
- Present
- Privileges needed
- None
- User interaction
- None
- Confidentiality
- None
- Integrity
- None
- Availability
- High
Raw vector
CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
