Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2024-42479— llama.cpp allows write-what-where in rpc_server::set_tensor

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 data 指针可导致任意地址写入。

CVSS 10.0 · Critical EPSS 2.61% · P85

Possible ATT&CK Techniques 1 AI

T1055 · Process Injection
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2024-42479

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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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 allows write-what-where in rpc_server::set_tensor
Source: CVE Program / CVE List V5
Vulnerability 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.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
Source: CVE Program / CVE List V5
Vulnerability Type
任意地址可写任意内容条件
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 data 指针可导致任意地址写入。
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)

Shenlong Deep Dive — AI Deep Analysis

10-question deep dive: root cause, exploitation, mitigation, urgency. Read summary free, full version requires login.

Read summary Full analysis (login)

Affected Products

Vendor Product Affected Versions CPE Subscribe
ggerganov llama.cpp < b3561 -

II. Public POCs for CVE-2024-42479

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2024-42479

请登录查看更多情报信息。

Vendor Advisories for CVE-2024-42479 (1)

Same Patch Batch · ggerganov · 2024-08-12 · 3 CVEs total

CVE-2024-42477 5.3 MEDIUM llama.cpp global-buffer-overflow in ggml_type_size
CVE-2024-42478 5.3 MEDIUM llama.cpp allows Arbitrary Address Read in rpc_server::get_tensor

IV. Related Vulnerabilities

Same product: llama.cpp
Same vendor: ggerganov
Same weakness: CWE-123

V. Comments for CVE-2024-42479

No comments yet

Leave a comment