CVE Feed

    Dashboard / CVE / CVE-2026-100652

    CVE-2026-100652

    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.

    Published:Sep 26, 2026
    Last Modified:Sep 28, 2026
    EPS:Sep 26, 2026
    EPSS Score:0.00329
    CVSS Score:5.9

    Affected Products

    Vendor
    Vllm
    Product
    Vllm
    Vendor
    Vllm-project
    Product
    Vllm

    Exploits

    https://github.com/vllm-project/vllm/security/advisories/GHSA-qff2-492f-9fm4

    Common Attack Pattern Enumeration and Classification (CAPEC)

    CAPEC-10 Buffer Overflow via Environment Variables
    CAPEC-101 Server Side Include (SSI) Injection
    CAPEC-104 Cross Zone Scripting
    CAPEC-108 Command Line Execution through SQL Injection
    CAPEC-109 Object Relational Mapping Injection
    CAPEC-110 SQL Injection through SOAP Parameter Tampering
    CAPEC-120 Double Encoding
    CAPEC-13 Subverting Environment Variable Values
    CAPEC-135 Format String Injection
    CAPEC-136 LDAP Injection
    CAPEC-14 Client-side Injection-induced Buffer Overflow
    CAPEC-153 Input Data Manipulation
    CAPEC-182 Flash Injection
    CAPEC-209 XSS Using MIME Type Mismatch
    CAPEC-22 Exploiting Trust in Client
    CAPEC-23 File Content Injection
    CAPEC-230 Serialized Data with Nested Payloads
    CAPEC-231 Oversized Serialized Data Payloads
    CAPEC-24 Filter Failure through Buffer Overflow
    CAPEC-250 XML Injection
    CAPEC-261 Fuzzing for garnering other adjacent user/sensitive data
    CAPEC-267 Leverage Alternate Encoding
    CAPEC-28 Fuzzing
    CAPEC-3 Using Leading 'Ghost' Character Sequences to Bypass Input Filters
    CAPEC-31 Accessing/Intercepting/Modifying HTTP Cookies
    CAPEC-42 MIME Conversion
    CAPEC-43 Exploiting Multiple Input Interpretation Layers
    CAPEC-45 Buffer Overflow via Symbolic Links
    CAPEC-46 Overflow Variables and Tags
    CAPEC-47 Buffer Overflow via Parameter Expansion
    CAPEC-473 Signature Spoof
    CAPEC-52 Embedding NULL Bytes
    CAPEC-53 Postfix, Null Terminate, and Backslash
    CAPEC-588 DOM-Based XSS
    CAPEC-63 Cross-Site Scripting (XSS)
    CAPEC-64 Using Slashes and URL Encoding Combined to Bypass Validation Logic
    CAPEC-664 Server Side Request Forgery
    CAPEC-67 String Format Overflow in syslog()
    CAPEC-7 Blind SQL Injection
    CAPEC-71 Using Unicode Encoding to Bypass Validation Logic
    CAPEC-72 URL Encoding
    CAPEC-73 User-Controlled Filename
    CAPEC-78 Using Escaped Slashes in Alternate Encoding
    CAPEC-79 Using Slashes in Alternate Encoding
    CAPEC-8 Buffer Overflow in an API Call
    CAPEC-80 Using UTF-8 Encoding to Bypass Validation Logic
    CAPEC-81 Web Server Logs Tampering
    CAPEC-83 XPath Injection
    CAPEC-85 AJAX Footprinting
    CAPEC-88 OS Command Injection
    CAPEC-9 Buffer Overflow in Local Command-Line Utilities

    Related CVEs

    CVE-2026-115918 (CVSS 6.5) — vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses…
    CVE-2026-115917 (CVSS 3.4) — vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the OpenAI-compatible serv…
    CVE-2026-115916 (CVSS 6.5) — vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py comp…
    CVE-2026-115915 (CVSS 8.1) — vLLM is an inference and serving engine for large language models. Prior to 0.32.0, ImageMediaIO passes attack…
    CVE-2026-115914 (CVSS 6.5) — vLLM is an inference and serving engine for large language models. From 0.11.1 until 0.32.0, the DeepSeek-OCR,…
    CVE-2026-115913 (CVSS 6.5) — vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the Phi-4 multimodal audio…
    CVE-2026-115912 (CVSS 7.5) — vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller ca…
    CVE-2026-115911 (CVSS 6.5) — vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated cal…
    CVE-2026-116180 (CVSS 8.3) — vLLM from 0.8.5 before 0.31.0 has a denial of service flaw. LogprobsTensors.empty_cpu() in vllm/v1/outputs.py …
    CVE-2026-116181 (CVSS 7.1) — vLLM from 0.20.1 before 0.29.0 contains an improper input validation vulnerability that allows remote attacker…

    Common Vulnerability Scoring System

    Attack Vector
    Network
    Adjacent
    Local
    Physical
    Privileges Required
    None
    Low
    High
    User Interaction
    None
    Required
    Scope
    Unchanged
    Changed
    Confidentiality
    None
    Low
    High
    Integrity
    None
    Low
    High
    Availability
    None
    Low
    High