Out-of-bounds Read in Ggerganov Llama.cpp
CVE-2024-42478
llama.cpp provides LLM inference in C/C++. The unsafe `data` pointer member in the `rpc_tensor` structure can cause arbitrary address reading. This vulnerability is fixed in b3561.
Vulnerability class: Buffer Overflow
EPSS: 0.005 (65.9th percentile) — read the EPSS interpretation.
CVSS v3 metric
CVSS v3 base score 5.3 (Medium). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N.
Affected products
- Ggerganov Llama.cpp — versions < b3561
Weakness classification (CWE)
Public proof-of-concept exploits
References
- https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-5vm9-p64x-gqw9 (x_refsource_CONFIRM)
- https://github.com/ggerganov/llama.cpp/commit/b72942fac998672a79a1ae3c03b340f7e629980b (x_refsource_MISC)
Frequently asked questions
- What is CVE-2024-42478?
- CVE-2024-42478 is a medium-severity vulnerability in Ggerganov Llama.cpp, classified under Out-of-bounds Read. CVSS score: 5.3/10. Published 2024-08-12.
- How severe is CVE-2024-42478?
- Medium severity. CVSS v3 base score is 5.3 out of 10.
- Is CVE-2024-42478 known to be exploited?
- 3 public proof-of-concept repositories are indexed. Not currently listed in the CISA KEV catalog.