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.
Metrics
Affected Vendors & Products
References
History
Thu, 06 Aug 2026 22:15:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| 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. | |
| Title | llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints | |
| Weaknesses | CWE-367 CWE-416 |
|
| References |
| |
| Metrics |
cvssV3_1
|
Status: PUBLISHED
Assigner: VulnCheck
Published:
Updated: 2026-08-06T15:53:19.379Z
Reserved: 2026-05-01T18:22:45.641Z
Link: CVE-2026-43632
No data.
No data.
No data.
OpenCVE Enrichment
Updated: 2026-08-07T01:15:05Z