GitHub_MVULNRICHMENT:CVE-2024-42479CVE-2024-42479 llama.cpp allows write-what-where in rpc_server::set_tensor
CVSS3
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
NONE
User Interaction
NONE
Scope
CHANGED
Confidentiality Impact
HIGH
Integrity Impact
HIGH
Availability Impact
HIGH
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
AI Score
Confidence
High
EPSS
Percentile
38.0%
SSVC
Exploitation
poc
Automatable
no
Technical Impact
total
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.
CNA Affected
[
{
"vendor": "ggerganov",
"product": "llama.cpp",
"versions": [
{
"status": "affected",
"version": "< b3561"
}
]
}
]ADP Affected
[
{
"cpes": [
"cpe:2.3:a:ggerganov:llama.cpp:*:*:*:*:*:*:*:*"
],
"vendor": "ggerganov",
"product": "llama.cpp",
"versions": [
{
"status": "affected",
"version": "0",
"lessThan": "b3561",
"versionType": "custom"
}
],
"defaultStatus": "unknown"
}
]Related
CVSS3
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
NONE
User Interaction
NONE
Scope
CHANGED
Confidentiality Impact
HIGH
Integrity Impact
HIGH
Availability Impact
HIGH
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
AI Score
Confidence
High
EPSS
Percentile
38.0%
SSVC
Exploitation
poc
Automatable
no
Technical Impact
total