CVE-2026-43632
CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
Summary
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 Software
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| ggml-org | llama.cpp | b7492 <= b9060 | affected |
Weaknesses
- CWE-416: Use After Free
- CWE-367: Time-of-check Time-of-use (TOCTOU) Race Condition
ADP Enrichment
CISA ADP Vulnrichment
- SSVC:
- Exploitation: none
- Automatable: no
- Technical Impact: total
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
Feedback
Was this page helpful?
Glad to hear it! Please tell us how we can improve.
Sorry to hear that. Please tell us how we can improve.