CVE-2024-42479

moderate-risk
Published 2024-08-12

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.

Do I need to act?

~
5.7% chance of exploitation in next 30 days
EPSS score — moderate exploit probability
-
Not on CISA KEV list
No confirmed active exploitation reported to CISA
+
Fix available
Upgrade to: b72942fac998672a79a1ae3c03b340f7e629980b, b72942fac998672a79a1ae3c03b340f7e629980b
10
CVSS 10.0/10 Critical
NETWORK / LOW complexity

Affected Products (1)

Llama.Cpp

Affected Vendors

Ggerganov

References (2)

Patch https://github.com/ggerganov/llama.cpp/commit/b72942fac998672a79a1ae3c03b340f7e6...
Exploit https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-wcr5-566p-9cwj
47
/ 100
moderate-risk
Severity 33/34 · Critical
Exploitability 9/34 · Low
Exposure 5/34 · Minimal