Skip to main content

Over 150 LLM Providers · Over 5,300 Models The most extensible AI-powered pentesting platform. Open source. Star on GitHub

CVE-2025-49847

8.8 · HIGH
Published Jun 17, 2025 ggml CWE-119 EPSS 0.44% (37th pctl)

Overview

CVE-2025-49847 is a high-severity vulnerability affecting ggml llama.cpp. It was published on June 17, 2025 and has a CVSS 3.1 base score of 8.8 (HIGH).

This vulnerability has a CVSS 3.1 base score of 8.8, rated HIGH. It can be exploited remotely over the network. No authentication or special privileges are required for exploitation.

Technical Description

llama.cpp is an inference of several LLM models in C/C++. Prior to version b5662, an attacker‐supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp’s vocabulary‐loading code. Specifically, the helper _try_copy in llama.cpp/src/vocab.cpp: llama_vocab::impl::token_to_piece() casts a very large size_t token length into an int32_t, causing the length check (if (length < (int32_t)size)) to be bypassed. As a result, memcpy is still called with that oversized size, letting a malicious model overwrite memory beyond the intended buffer. This can lead to arbitrary memory corruption and potential code execution. This issue has been patched in version b5662.

Remediation

Check the references section for vendor advisories and patches from ggml. Update llama.cpp to the latest patched version. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.

Affected Products

Vendor Product Versions Status
ggml llama.cpp >= 0, < b5662 Affected

Frequently Asked Questions

What is CVE-2025-49847?

CVE-2025-49847 is a high-severity vulnerability affecting ggml llama.cpp. It was published on June 17, 2025 and has a CVSS 3.1 base score of 8.8 (HIGH).

How severe is CVE-2025-49847?

This vulnerability has a CVSS 3.1 base score of 8.8, rated HIGH. It can be exploited remotely over the network. No authentication or special privileges are required for exploitation.

How do I fix or remediate CVE-2025-49847?

Check the references section for vendor advisories and patches from ggml. Update llama.cpp to the latest patched version. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.

How can CyberStrike help with CVE-2025-49847?

CyberStrike's AI-powered security agents can automatically detect CVE-2025-49847 across your infrastructure using autonomous pentesting, DAST scanning, and HackBrowser. The platform continuously monitors for known vulnerabilities and provides actionable remediation guidance prioritized by real-world exploitability.