CVE-2024-42477

HIGH EPSS 36.6%
Published Aug 12, 20241y ago · Modified Jun 17, 20262w ago
7.5 CVSS 3.1
High
Find Similar
Published Aug 12, 2024 1y ago
Last Modified Jun 17, 2026 2w ago

Description

llama.cpp provides LLM inference in C/C++. The unsafe `type` member in the `rpc_tensor` structure can cause `global-buffer-overflow`. This vulnerability may lead to memory data leakage. The vulnerability is fixed in b3561.

CVSS Details

Base Score
7.5
Exploitability
3.9
Impact
3.6
Vector string
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Attack Vector Network
Attack Complexity Low
Privileges Required None
User Interaction None
Scope Unchanged
Confidentiality None
Integrity None
Availability High

Threat Intelligence

EPSS Exploit Probability
36.6% percentile
Exploit & Patch Status
No Known Exploit
Patch Available

Weaknesses 2

CWE-125 Out-of-bounds Read Memory Safety
CWE-401

Affected Products 1

VendorProductVersionRange
ggmlllama.cpp* <b3561

References 2

  • github.com https://github.com/ggerganov/llama.cpp/commit/b72942fac998672a79a1ae3c03b340f7e629980b
    Patch
  • github.com https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-mqp6-7pv6-fqjf
    Vendor Advisory

Remediation

  • github.com https://github.com/ggerganov/llama.cpp/commit/b72942fac998672a79a1ae3c03b340f7e629980b
    Patch