Skip to content
Fencer Vulns
high 8.8

CVE-2025-49847 json

llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model

published 2025-06-17 16 mo ago modified 2026-06-17 4 mo ago also EUVD-2025-18632

cvss
8.8
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.5%
EPSS 0.5% chance of exploitation in 30 days, percentile 44%
public exploits
0
none known

Summary

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.

Patch / fix

  • ggml llama.cpp b5662
  • llama.cpp Debian 14 5713+dfsg-1

debian advisories DEBIAN-CVE-2025-49847

  • llamacpp openSUSE Tumbleweed 5699-1.1

opensuse advisories openSUSE-SU-2025:15245-1

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2025-49847 updated cvss 8.8

llama-cpp: llama.cpp Buffer Overflow

  • Red Hat All currently supported Red Hat products
    not affected: vulnerable code not present

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
Proof of concept is public
Automatable
no
Technical impact
total
Assessed
16 mo ago

Exploit prediction

0.52% chance of exploitation in the next 30 days, higher than 44% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by version score vector
CNA 3.1 8.8 CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Affected products

  • ggml-org llama.cpp

Classification

Weakness
  • CWE-119 Improper Restriction of Operations within the Bounds of a Memory Buffer
  • CWE-195 Signed to Unsigned Conversion Error

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.