Lucene search
+L

5 matches found

Cvelist
Cvelist
•added 2026/10/29 1:08 p.m.•35 views

CVE-2026-119052 llama.cpp b2877 before b11935 ggml-rpc Server DoS via Oversized recv_msg Length

llama.cpp b2877 before b11935 contains an uncaught exception vulnerability in the ggml-rpc server that allows unauthenticated remote attackers to crash the rpc-server by sending oversized message lengths. After the HELLO handshake, attackers can send a command such as SETTENSOR with a length abov...

8.7CVSS0.00659EPSS
SaveExploits1References6
CVE
CVE
•added 2026/10/29 1:08 p.m.•29 views

CVE-2026-119052

The llama.cpp project (versions b2877 before b11935 ) is vulnerable to a Denial of Service (DoS) attack in the ggml-rpc server. An unauthenticated remote attacker can crash the rpc-server by sending a command, such as SET_TENSOR , with a length exceeding std::vector::max_size(). This triggers an ...

8.7CVSS6.2AI score0.00659EPSS
SaveExploits1References6Affected Software1
osv_cve
osv_cve
•added 2026/10/29 1:08 p.m.•23 views

CVE-2026-119052 llama.cpp b2877 before b11935 ggml-rpc Server DoS via Oversized recv_msg Length

llama.cpp b2877 before b11935 contains an uncaught exception vulnerability in the ggml-rpc server that allows unauthenticated remote attackers to crash the rpc-server by sending oversized message lengths. After the HELLO handshake, attackers can send a command such as SETTENSOR with a length abov...

8.7CVSS6.1AI score
SaveExploits0References8
CNNVD
CNNVD
•added 2026/10/29 12:00 a.m.•15 views

ggml llama.cpp improper exception handling vulnerability

Versions of ggml llama.cpp from b2877 up to and including b11935 contain an improper exception handling vulnerability. This vulnerability arises because the ggml-rpc server fails to catch exceptions; an unauthenticated remote attacker can send a SETTENSOR command with a length exceeding...

8.7CVSS6AI score0.00659EPSS
SaveExploits1References7
Vulnrichment
Vulnrichment
•added 2024/08/12 3:07 p.m.•50 views

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

llama.cpp provides LLM inference in C/C++. The unsafe data pointer member in the rpctensor structure can cause arbitrary address writing. This vulnerability is fixed in b3561...

10CVSS6AI score0.02607EPSS
SaveExploits1References2
Rows per page
Query Builder