CVE-2026-34159
Memory buffer overflow in Ggml Llama.cpp
CVSS score
9.8
EPSS probability
%1.6
Risk score
0.2
Published
6 mo ago
Public Exploits · GitHub and Metasploit Intelligence
This tab scans the sources that NVD labels as exploits, GitHub repositories matching the CVE identifier and Rapid7 Metasploit Framework modules. Only links to sources that were actually found are shown.
GitHub
0 Click RCE exploit for CVE-2026-34159 Lama.cpp RPC server (★0)
Makefile Go / Python
Critical buffer validation bypass in deserialize_tensor() (llama.cpp < b8492). Null tensor buffer skips bounds check, enabling unauthenticated arbitrary R/W via GRAPH_COMPUTE. ASLR bypass + RCE over TCP 50052. (★0)
Makefile Go / Python
https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-j8rj-fmpv-wcxw
Makefile Go / Python
Similar Vulnerabilities
9.2
CVE-2026-43629llama.cpp b4882–b9058 Buffer Overflow in KV Cache State Restore
Patch verifiedEPSS %1
9.2
CVE-2026-43631llama.cpp b7492–b9060 Use-After-Free RCE via llama-server
Patch verifiedEPSS %1
7.5
9.2
CVE-2026-43632llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints
Patch verifiedEPSS %0
7.5
7.5
Get this vulnerability through the API
Affected products, version ranges, exploitation status and patch information in a single request, with a free key.
curl -H "x-api-key: $DAYBREACH_API_KEY" \ "https://api.daybreach.dev/api/v1/intel/cves/CVE-2026-34159"