Vulnerability details
CVE-2026-43632
ggml-org llama.cpp
llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints
CVSS 4.0
9.2Critical
Official 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.
CVSS scores
| Score | Version | Source | Vector |
|---|---|---|---|
| 9.2Critical | 4.0 | CVEProject cvelistV5 (CNA) (VulnCheck) | 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 |
| 8.1High | 3.1 | CVEProject cvelistV5 (CNA) (VulnCheck) | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H |
Affected products
| Vendor | Product | Versions | Source |
|---|---|---|---|
| ggml-org | llama.cpp | b7492 ≤ v ≤ b9060 | CVEProject cvelistV5 (CNA) |
References and advisories
2
Kolun on Telegram @kolunsec
Exploited CVEs, key news and a daily digest
Alerts for this product's next CVEsFollow the product to get new vulnerabilities on Telegram.
Details
- Published
- 2026-08-06
- Last updated
- 2026-08-14
- State
- Published
- Assigner (CNA)
- VulnCheck
Exploit prediction (EPSS)
0.47%
Probability of exploitation in 30 days
41.4%
Percentile (among all CVEs)
SSVC assessment (CISA)
- Automatable
- No
- Exploitation
- None
- Technical impact
- Total
Weaknesses (CWE)
- CWE-416Use After Free
- CWE-367Time-of-check Time-of-use (TOCTOU) Race Condition