CVE-2024-32878
There is a use of uninitialized heap variable vulnerability in gguf_init_from_file, the code will free this uninitialized variable later.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.70%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
Description
Llama.cpp is LLM inference in C/C++. There is a use of uninitialized heap variable vulnerability in gguf_init_from_file, the code will free this uninitialized variable later. In a simple POC, it will directly cause a crash. If the file is carefully constructed, it may be possible to control this uninitialized value and cause arbitrary address free problems. This may further lead to be exploited. Causes llama.cpp to crash (DoS) and may even lead to arbitrary code execution (RCE). This vulnerability has been patched in commit b2740.
- 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
- 0.70% probability · 51th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-456
- Affected
- ggml/llama.cpp
- Source
- security-advisories@github.com
References
- https://github.com/ggerganov/llama.cpp/releases/tag/b2749Release Notes
- https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-p5mv-gjc5-mwqvVendor Advisory
- https://github.com/ggerganov/llama.cpp/releases/tag/b2749Release Notes
- https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-p5mv-gjc5-mwqvVendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.