CVE-2026-93989
Published:September 19, 2026
Updated:September 22, 2026
vLLM through 0.29.0 fails to properly validate bad_words token indices against the model's generation output width in SamplingParams.update_from_tokenizer(). Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests to return incorrect tokens.
Related Resources (6)
Do you need more information?
Contact UsCVSS v4
Base Score:
2.3
Attack Vector
NETWORK
Attack Complexity
HIGH
Attack Requirements
PRESENT
Privileges Required
LOW
User Interaction
NONE
Vulnerable System Confidentiality
NONE
Vulnerable System Integrity
LOW
Vulnerable System Availability
NONE
Subsequent System Confidentiality
NONE
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
3.1
Attack Vector
NETWORK
Attack Complexity
HIGH
Privileges Required
LOW
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
NONE
Integrity
LOW
Availability
NONE
Weakness Type (CWE)
Improper Validation of Array Index
EPSS
Base Score:
0.20