llama.cpp builds b1283 through b9058 contain an integer overflow vulnerability in the llamabatchinit() function where unchecked multiplications in malloc() calls can wrap past INT32MAX when computing allocation sizes. Attackers can pass specially crafted parameters to trigger integer overflow, causing heap corruption and potentially achieving arbitrary code execution through subsequent batch operations that write past allocated buffer boundaries.

llama.cpp builds b3978 through b9058 contain an integer underflow and out-of-bounds read vulnerability in the DRY sampler that allows unauthenticated attackers to trigger a heap buffer underflow by sending a crafted HTTP request with dryallowedlength set to INT32MIN to the /v1/completions or /v1/chat/completions endpoints. Attackers can exploit this vulnerability to crash the server with SIGSEGV causing denial of service for all connected users, or corrupt token sampling probabilities by reading garbage values from memory before the allocated buffer.

llama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path where the statereaddata() function computes write size without overflow checking, allowing attackers with write access to the slotsavepath directory to corrupt heap memory. Attackers can craft malicious state files where cellcount 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.