CVE-2024-32878
7.1
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:L
Summary
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.
Affected Software
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| ggerganov | llama.cpp | <= b2715 | affected |
Weaknesses
- CWE-456: CWE-456: Missing Initialization of a Variable
ADP Enrichment
CISA ADP Vulnrichment
- SSVC:
- Exploitation: poc
- Automatable: no
- Technical Impact: total
CVE Program Container
Additional References
- https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-p5mv-gjc5-mwqv
- https://github.com/ggerganov/llama.cpp/releases/tag/b2749
References
- https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-p5mv-gjc5-mwqv
- https://github.com/ggerganov/llama.cpp/releases/tag/b2749
Feedback
Was this page helpful?
Glad to hear it! Please tell us how we can improve.
Sorry to hear that. Please tell us how we can improve.