Vulnerability · Published Aug 12, 2024 · Assigned by GitHub_M

CVE-2024-42478llama.cpp allows Arbitrary Address Read in rpc_server::get_tensor

Medium 5.3

In plain English

A medium-severity out-of-bounds read in llama.cpp from ggerganov. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.6% (higher than 49% of all known vulnerabilities).

Severity (CVSS 3.1)5.3Medium
Exploit odds (30 days)0.6%top 51.2% of all CVEs
Exploited in the wildNo reportsCISA SSVC: poc
Attack toolingNoneno public tooling known

Official description

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.

Affected products (as reported)

VendorProductVersions
ggerganov llama.cpp < b3561

Weakness: CWE-125 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N

References