CVE-2026-27940 json
llama.cpp has a Heap Buffer Overflow via Integer Overflow in `mem_size` Calculation — Bypass of CVE-2025-53630 Fix
published 2026-03-12 7 mo ago modified 2026-06-17 4 mo ago also EUVD-2026-11605
- 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 11%
- public exploits
- 0
- none known
Summary
llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the gguf_init_from_file_impl() in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread() writes 528+ bytes of attacker-controlled data past the buffer boundary. This is a bypass of a similar bug in the same file - CVE-2025-53630, but the fix overlooked some areas. This vulnerability is fixed in b8146.
Patch / fix
- ggerganov llama.cpp b8146
- ggml llama.cpp b8146
- llama.cpp Debian 14 8461+dfsg-1
debian advisories DEBIAN-CVE-2026-27940
Vendor advisories
What the vendors themselves say about their products: affected, fixed or not affected, and what to do.
red hat product security vex CVE-2026-27940 updated cvss 7.8
llama.cpp: heap-based buffer overflow via integer overflow in mem_size calculation (bypass of CVE-2025-53630 fix)
-
Red Hat All currently supported Red Hat productsnot affected: vulnerable code not present
Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- no
- Technical impact
- total
- Assessed
- 7 mo ago
Exploit prediction
0.21% chance of exploitation in the next 30 days, higher than 11% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-3p4r-fq3f-q74v referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 7.8 | CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |
Affected products
- ggml-org llama.cpp
Classification
References
-
github.com
/ggml-org/llama.cpp/security/advisories/GHSA-3p4r-fq3f-q74v
exploit, vendor-advisory
Sources
- CVE List CVE-2026-27940
- NVD CVE-2026-27940
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.