CVE-2024-42477 | BDVDB-2026-245145 Detail

ggerganovllama.cpp

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.

Impact#

Per CVSS v3.1: confidentiality impact low, integrity impact none, availability impact none. Attack vector: network.

Weaknesses#

CWE-125 Out-of-bounds Read

References#

Exploit#

No public exploit known

History#

Version 12024-08-12Record published in the CVE List.
Version 22024-08-13Most recent update recorded in the CVE List.

Published

Published: 2024-08-12
Last modified: 2024-08-13

Vendor information

Vendor: ggerganov
Product: llama.cpp

All ggerganov vulnerabilities

Score

5.3 Medium

EPSS

less than 1%, Very Low

Estimated chance of exploitation in the next 30 days. EPSS percentile: 39.9.

KEV

Not listed in the CISA Known Exploited Vulnerabilities catalog.

Impact

Memory Corruption

Action

No specific action is recorded in the source data. Check the references for vendor guidance.

Affected Systems

Vulnerable
< b3561
Fixed
Not stated

Scoring System

CVSS v4.0

Not available

CVSS v3.1

5.3 Medium

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N

Metric breakdown
Attack Vector	Network
Attack Complexity	Low
Privileges Required	None
User Interaction	None
Scope	Unchanged
Confidentiality	Low
Integrity	None
Availability	None

CVSS v3.0

Not available

CVSS v2

Not available

Source: CVE List v5 (record); CISA KEV (kev, action); FIRST EPSS (epss).