CVE-2024-42479
llama.cpp allows write-what-where in rpc_server::set_tensor
Severity Score
10.0
*CVSS v3.1
Exploit Likelihood
*EPSS
Affected Versions
*CPE
Public Exploits
0
*Multiple Sources
Exploited in Wild
-
*KEV
Decision
Attend
*SSVC
Descriptions
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.
*Credits:
N/A
CVSS Scores
Attack Vector
Attack Complexity
Privileges Required
User Interaction
Scope
Confidentiality
Integrity
Availability
* Common Vulnerability Scoring System
SSVC
- Decision:Attend
Exploitation
Automatable
Tech. Impact
* Organization's Worst-case Scenario
Timeline
- 2024-08-02 CVE Reserved
- 2024-08-12 CVE Published
- 2024-08-13 CVE Updated
- 2024-08-16 EPSS Updated
- ---------- Exploited in Wild
- ---------- KEV Due Date
- ---------- First Exploit
CWE
- CWE-123: Write-what-where Condition
CAPEC
References (2)
URL | Tag | Source |
---|---|---|
https://github.com/ggerganov/llama.cpp/commit/b72942fac998672a79a1ae3c03b340f7e629980b | X_refsource_misc | |
https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-wcr5-566p-9cwj | X_refsource_confirm |
URL | Date | SRC |
---|
URL | Date | SRC |
---|
URL | Date | SRC |
---|