- 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.
- Source
- security-advisories@github.com
- NVD status
- Awaiting Analysis
CVSS 3.1
- Type
- Secondary
- Base score
- 8.8
- Impact score
- 5.9
- Exploitability score
- 2.8
- Vector string
- CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
- Severity
- HIGH
- security-advisories@github.com
- CWE-119
- Hype score
- Not currently trending
[CVE-2025-49847: HIGH] Security Alert: Vulnerability in llama.cpp prior to b5662 allows buffer overflow through malicious GGUF model vocabulary. Update to version b5662 to fix the issue. #cybersecurity#cve,CVE-2025-49847,#cybersecurity https://t.co/lcGif7BpQp https://t.co/BFUpQiS
@CveFindCom
18 Jun 2025
47 Impressions
0 Retweets
0 Likes
0 Bookmarks
0 Replies
0 Quotes
CVE-2025-49847 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.cp… https://t.co/H3VrTCq2Lp
@CVEnew
17 Jun 2025
318 Impressions
0 Retweets
0 Likes
1 Bookmark
0 Replies
0 Quotes