CVE-2026-27940Disclosure(ggml / llama.cpp)

LOWCVSS 7.8 · HIGH

Signal is active with 1 mentions in latest observed window

Immediate actions

Patch ggml llama.cpp systems immediately

Recommended action window: Monitor and triage in normal cycle

NVD 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.

ggml CVEs Back to dashboard

0.5/ 10 priority

Sources & remediation

Exploit / PoC references

https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-3p4r-fq3f-q74v

Weakness type (CWE)

CWE-122CWE-190

Priority

LOW

Exploitation

NONE

PoC

YES

Patch

AVAILABLE

Momentum

STABLE

Are you affected?

If you run products in this scope, you should treat this CVE as relevant to your environment.

llama.cpp

Threat summary

Patch or workaround signal is available
4 mentions across 2 observed days
Momentum state: stable

What's happening

Patch or workaround mentioned in 1 signal
Technical details provided in 4 signals
Disclosure: 3 classified signals
General: 1 classified signal
Peaked 1d ago at 3 mentions (2026-03-12); latest day: 1
4 total mentions across 2 days

Affected systems

Vendors

ggml

Products

llama.cpp

Deep dive

Activity timeline4 mentions / 2d

Signal classification2 categories

Disclosure

375.0%

General

125.0%

Referenced assets4 URLs

By indicator

Classification over time

Date	Total	Labels

2026-03-12	3	Disclosure3
2026-03-18	1	General1

Full discourse4 posts

Aditya Gupta@adi1391211d
Disclosure
doing my part to make the ai ecosystem safer. starting with llama.cpp Heap Overflow Bug identified using CFSE World Modeling. Just received : CVE-2026-27940 one step at a time. thanks @ggerganov for prioritizing security and fixing at such light-speed 🙏 https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-3p4r-fq3f-q74v
Post summary
A heap–overflow vulnerability (CVE‑2026‑27940) in llama.cpp has been identified; a fix is being released swiftly by the maintainer.
00040726
8.2K followersView on X
Vulmon Vulnerability Feed@VulmonFeeds210d
Disclosure
CVE-2026-27940 Integer Overflow in llama.cpp gguf_init_from_file_impl() Leading to Heap Buffer Overflow https://vulmon.com/vulnerabilitydetails?qid=CVE-2026-27940
Post summary
The post discloses an integer overflow flaw in llama.cpp that could cause a heap buffer overflow, but it provides neither a PoC, exploit code, active exploitation evidence, nor a mitigation strategy.
0001020
4.0K followersView on X
IntegSec@integ_sec205d
General
CVE-2026-27940: llama.cpp Integer Overflow - What It Means for Your Business and How to Respond https://hubs.li/Q047k0hK0
Post summary
The excerpt is a headline announcing CVE‑2026‑27940, describing it as an integer‑overflow issue in llama.cpp, but offers no PoC, exploit, active‑exploitation evidence, patch guidance, or debunking information.
0000028
29 followersView on X
CVE@CVEnew210d
Disclosure
CVE-2026-27940 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 … https://www.cve.org/CVERecord?id=CVE-2026-27940
Post summary
The post reports CVE-2026-27940 as an integer overflow vulnerability in llama.cpp’s gguf.cpp, but it does not mention a PoC, exploit code, active exploitation, or any patch.
00000150
56.7K followersView on X

CPE platform detail1 entries

Part:

Vendor:

Product:

Version:

Target SW:

Target HW:

1 of 1 entries

Part	Vendor	Product	Version	Target SW	Target HW
App	ggml	llama.cpp	-	-	-

Explore more

Back to dashboard ggml CVEs llama.cpp vulnerabilities

What researchers are saying

CVE-2026-27940

Aditya Gupta[verified]@adi1391Disclosure

A heap–overflow vulnerability (CVE‑2026‑27940) in llama.cpp has been identified; a fix is being released swiftly by the maintainer.

IntegSec[verified]@integ_secGeneral

The excerpt is a headline announcing CVE‑2026‑27940, describing it as an integer‑overflow issue in llama.cpp, but offers no PoC, exploit, active‑exploitation evidence, patch guidance, or debunking information.

Vulmon Vulnerability Feed@VulmonFeedsDisclosure

The post discloses an integer overflow flaw in llama.cpp that could cause a heap buffer overflow, but it provides neither a PoC, exploit code, active exploitation evidence, nor a mitigation strategy.

CVE@CVEnewDisclosure

The post reports CVE-2026-27940 as an integer overflow vulnerability in llama.cpp’s gguf.cpp, but it does not mention a PoC, exploit code, active exploitation, or any patch.