CVE-2026-43632
llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints
Using llama.cpp by ggml-org?
Get instant alerts when new vulnerabilities affect llama.cpp - before attackers find them.
Description
llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six tokenization endpoints (/tokenize, /detokenize, /infill, /apply-template, /rerank, and /anthropic/count_tokens) that bypass the task queue and access ctx_server.vocab directly on HTTP worker threads. Attackers can exploit a time-of-check-time-of-use race condition where the main thread destroys and frees vocab after the synchronization lock is released but before the handler finishes using it, causing a crash or potential code execution when --sleep-idle-seconds is configured.
Affected
Our own answer: ranges merged, affected separated from platform-only, with confidence and review flags.
Remediation
No guide yetNo remediation guidance has been written for this CVE yet. What the record does show:
References (2)
SSVC — Action Prioritization
SSVC signals action urgency (what to patch first), separate from CVSS which measures severity.
CVSS
- Attack Vector
- NETWORK
- Complexity
- HIGH
- Privileges
- NONE
- User Interaction
- NONE
- Scope
- UNCHANGED
- Confidentiality
- HIGH
- Integrity
- HIGH
- Availability
- HIGH
Quick Info
Get alerted
Stop reading CVE feeds looking for your own stack
Track the products you run and VulnTracker tells you when a new CVE affects them — with what is known about fixing it, and nothing about the rest.