What’s Vulnerable › Vulnerabilities

CVE-2025-49847: llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model

• Severity: high (CVSS 8.8 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.5% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2025-06-17 · updated 2026-06-17
• Weakness: CWE-119

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.

Affected products

• ggml-org llama.cpp: before b5662 — fixed in b5662

How to fix

Upgrade to a fixed version: ggml-org llama.cpp b5662. Check the vendor advisory for mitigations.

References

• https://github.com/ggml-org/llama.cpp/commit/3cfbbdb44e08fd19429fed6cc85b982a91f0efd5
• https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8wwf-w4qm-gpqr

Get alerted when CVE-2025-49847 or the next vulnerability affects your stack