CyberRota Analysis
AI-GeneratedA heap buffer overflow vulnerability exists in the KV cache state restore path of llama.cpp builds b4882 through b9058, allowing attackers with write access to the slot_save_path directory to exploit this flaw. By crafting malicious state files, attackers can manipulate memory allocation, leading to potential heap metadata corruption, model weight corruption, or arbitrary code execution. Organizations utilizing affected versions of llama.cpp should prioritize patching this vulnerability to mitigate the risk of exploitation.
Public Exploit Signal
A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.
Note: these links are listed for security research and verification purposes only.
Original NVD Description
llama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path where the state_read_data() function computes write size without overflow checking, allowing attackers with write access to the slot_save_path directory to corrupt heap memory. Attackers can craft malicious state files where cell_count multiplication overflows or exceeds tensor buffer allocation to write attacker-controlled bytes past buffer boundaries, potentially resulting in heap metadata corruption, model weight corruption, or arbitrary code execution via function pointer overwrite.