CVE-2026-27940
Prior to b8146, the gguf_init_from_file_impl() in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.18%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
Description
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.
- CVSS 3.1
- 7.8 HIGHCVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
- EPSS
- 0.18% probability · 7th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-122, CWE-190
- Affected
- ggml/llama.cpp
- Source
- security-advisories@github.com
References
- https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-3p4r-fq3f-q74vExploit, Vendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.