CVE-2026-43628 json
llama.cpp b3978–b9058 Integer Underflow via DRY Sampler
published 2026-08-06 3 mo ago modified 2026-10-29 10 d ago also EUVD-2026-54283
- cvss
- 7.8
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.2%
- EPSS 0.2% chance of exploitation in 30 days, percentile 14%
- public exploits
- 0
- none known
Summary
llama.cpp builds b3978 through b9058 contain an integer underflow and out-of-bounds read vulnerability in the DRY sampler that allows unauthenticated attackers to trigger a heap buffer underflow by sending a crafted HTTP request with dry_allowed_length set to INT32_MIN to the /v1/completions or /v1/chat/completions endpoints. Attackers can exploit this vulnerability to crash the server with SIGSEGV causing denial of service for all connected users, or corrupt token sampling probabilities by reading garbage values from memory before the allocated buffer.
Patch / fix
CISA SSVC
- Exploitation
- none
- Automatable
- no
- Technical impact
- total
- Assessed
- 3 mo ago
Exploit prediction
0.23% chance of exploitation in the next 30 days, higher than 14% of all scored CVEs (FIRST EPSS, 2026-11-08).
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 4.0 | 8.5 | CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N |
| CNA | 3.1 | 7.8 | CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |
| CNA | 4.0 | 8.5 | CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X |
Affected products
- ggml-org llama.cpp
Classification
References
-
github.com
/Vladimir-tokarev-cyera/llama-cpp-security-patches
mitigation, patch, third-party-advisory
-
vulncheck.com
/advisories/llama-cpp-b3978-b9058-integer-underflow-via-dry-sampler
third-party-advisory, patch
Sources
- CVE List CVE-2026-43628
- NVD CVE-2026-43628
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.
CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.