CVE-2026-27940
llama.cpp has a Heap Buffer Overflow via Integer Overflow in mem_size Calculation — Bypass of CVE-2025-53630 Fix
- Published
- Mar 12, 2026
- Updated
- Mar 14, 2026
- Assigning CNA
- GitHub_M
- Evidence observed
- Aug 25, 2026
Primary CVSS
nvd · CVSS 3.1
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:HLow · next 30 days
- Percentile
- 7.5%
- Model date
- Sep 21, 2026
EPSS is a statistical estimate, not a certainty or a measure of impact. Combine it with CVSS, KEV status, exposure and your environment.
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.
Sources
1Proof-of-concept exploit for CVE-2026-27940, demonstrating the vulnerability and providing technical details for security research.
Responsible use
Use vulnerability information only on systems you own or are authorized to test. Kitploit links to public research metadata and does not store exploit code or malicious payloads.