Vulnerability · Published Aug 12, 2024 · Assigned by GitHub_M
CVE-2024-42479llama.cpp allows write-what-where in rpc_server::set_tensor
Critical 10.0
In plain English
A critical-severity security flaw 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 2.6% (higher than 85% of all known vulnerabilities).
Severity (CVSS 3.1)10.0Critical
Exploit odds (30 days)2.6%top 14.5% 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 writing. This vulnerability is fixed in b3561.
Affected products (as reported)
Weakness: CWE-123 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H