CVE-2024-42477— llama.cpp global-buffer-overflow in ggml_type_size
Quick assessment
Affected
ggerganov llama.cpp
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.
llama.cpp是Georgi Gerganov个人开发者的一个多模态模型。 llama.cpp 存在安全漏洞，该漏洞源于 rpc_tensor 结构体中的 type 成员可导致全局缓冲区溢出。
Possible ATT&CK Techniques 1 AI
T1056 · Input Capture
Get alerts for future matching vulnerabilities
Log in to subscribe
I. Basic Information for CVE-2024-42477
Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.
Vulnerability Title
llama.cpp global-buffer-overflow in ggml_type_size
Source: CVE Program / CVE List V5
Vulnerability 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.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
Source: CVE Program / CVE List V5
Vulnerability Type
跨界内存读
Source: CVE Program / CVE List V5
Vulnerability Title
llama.cpp 安全漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
llama.cpp是Georgi Gerganov个人开发者的一个多模态模型。 llama.cpp 存在安全漏洞，该漏洞源于 rpc_tensor 结构体中的 type 成员可导致全局缓冲区溢出。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)
Affected Products
II. Public POCs for CVE-2024-42477
| # | POC Description | Source Link | Shenlong Link |
|---|
AI-Generated POC
Premium
No public POC found.
Login to generate AI POCIII. Intelligence Information for CVE-2024-42477
请登录查看更多情报信息。
Vendor Advisories for CVE-2024-42477 (1)
-
https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-mqp6-7pv6-fqjf x_refsource_CONFIRM
Same Patch Batch · ggerganov · 2024-08-12 · 3 CVEs total
| CVE-2024-42479 | 10.0 CRITICAL | llama.cpp allows write-what-where in rpc_server::set_tensor |
| CVE-2024-42478 | 5.3 MEDIUM | llama.cpp allows Arbitrary Address Read in rpc_server::get_tensor |
IV. Related Vulnerabilities
Same product: llama.cpp
-
CVE-2026-86317
ggml-org llama.cpp RPC Server ggml-rpc.cpp deserialize_tenso -
CVE-2026-78148
ggml-org llama.cpp ggml-RPC Server ggml-rpc.cpp graph_comput -
CVE-2026-78147
ggml-org llama.cpp ggml-RPC Server ggml-rpc.cpp deserialize_ -
CVE-2026-43632
llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoin -
CVE-2026-43631
llama.cpp b7492–b9060 Use-After-Free RCE via llama-server
Same vendor: ggerganov
Same weakness: CWE-125
-
CVE-2026-104433
Mooncake before 0.3.12 Out-of-Bounds Read via P2P Handshake -
CVE-2026-79896
Fortra BoKS Manager boks_portmux TLS ClientHello out-of-boun -
CVE-2026-103678
Tnef: heap out-of-bounds read in get_rtf_data_from_buf() via -
CVE-2026-103641
Gegl: gegl04: gegl: out-of-bounds read in the radiance hdr u -
CVE-2026-47544
NVIDIA vGPU Linux越界读取致代码执行漏洞
V. Comments for CVE-2024-42477
No comments yet