What’s Vulnerable › Vulnerabilities

CVE-2026-43632: llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints

• Severity: high (CVSS 8.1 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.5% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-08-06 · updated 2026-10-23
• Weakness: CWE-367

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 products

• ggml-org llama.cpp: from b7492 through b9060

References

• https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches
• https://www.vulncheck.com/advisories/llama-cpp-b7492-b9060-use-after-free-in-tokenization-endpoints

Get alerted when CVE-2026-43632 or the next vulnerability affects your stack