VulnerabilityAnalyzed

CVE-2025-49847

Prior to version b5662, an attacker‐supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp’s vocabulary‐loading code.

HIGH 8.8EPSS 0.48%

Does this matter?

High impact if exploited, but EPSS currently rates exploitation as unlikely (0.48%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.

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.

CVSS 3.1: 8.8 HIGHCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
EPSS: 0.48% probability · 40th percentile
CISA KEV: Not listed
Weakness: CWE-119, CWE-195
Affected: ggml/llama.cpp
Source: security-advisories@github.com

References

https://github.com/ggml-org/llama.cpp/commit/3cfbbdb44e08fd19429fed6cc85b982a91f0efd5Patch
https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8wwf-w4qm-gpqrMitigation, Vendor Advisory

Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.