CVE-2026-27940
Ggml Llama.cpp buffer overflow
- Published12 Mar 2026
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 breakdown
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:HAffected products
Remediation
Related CVEs
Recent high-severity vulnerabilities sharing a weakness type.
Frequently asked
Is CVE-2026-27940 being actively exploited?
CVE-2026-27940 is not in the CISA KEV catalog. A public exploit reference exists, so treat it as exploitable. Its EPSS exploit probability is 0.18%.
How severe is CVE-2026-27940?
CVE-2026-27940 has a CVSS 3.1 base score of 7.8, rated high. EPSS estimates a 0.18% probability of exploitation.
Which products are affected by CVE-2026-27940?
Affected products include Ggml Llama.cpp.
How do I fix CVE-2026-27940?
Upgrade affected software to a fixed version, for example Ggml Llama.cpp b8146 or later, then confirm no affected versions remain in your inventory.
How Secuno handles this
Secuno correlates vulnerabilities like CVE-2026-27940 against the real software inventory on every managed device, as each hourly inventory arrives. Rather than a static severity, each match is scored in context: exploit availability, EPSS, the asset's exposure, and business criticality decide where it lands in the queue. If an affected version is present anywhere across your portfolio, it surfaces automatically with a prioritised remediation path.
Data from the NVD, CISA KEV catalog and FIRST EPSS. CVSS 3.1 base score shown where available.