CVE-2026-43632
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.
Published:Aug 6, 2026
Last Modified:Aug 14, 2026
EPS:Aug 6, 2026
EPSS Score:0.0033
CVSS Score:8.1
Affected Products
Vendor
Product
Action
Vendor
Ggml
Product
Llama.cpp
Ggml
Llama.cpp
Vendor
Ggml-org
Product
Llama.cpp
Ggml-org
Llama.cpp
Exploits
No exploit reference
Common Weakness Enumeration
Common Attack Pattern Enumeration and Classification (CAPEC)
Related CVEs
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
