What’s Vulnerable › Vulnerabilities
CVE-2026-27940: llama.cpp has a Heap Buffer Overflow via Integer Overflow in `mem_size` Calculation — Bypass of CVE-2025-53630 Fix
- Severity: high (CVSS 7.8 v3.1)
- Exploited in the wild: not listed in CISA KEV
- EPSS: 0.2% probability of exploitation in the next 30 days
- Public exploit or detection template: yes
- Published: 2026-03-12 · updated 2026-06-17
- Weakness: CWE-122
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.
Affected products
- ggml-org llama.cpp: before b8146 — fixed in b8146
How to fix
Upgrade to a fixed version: ggml-org llama.cpp b8146. Check the vendor advisory for mitigations.
References
Get alerted when CVE-2026-27940 or the next vulnerability affects your stack