CVE-2026-43631 llama.cpp b7492–b9060 Use-After-Free RCE via llama-server

llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in the vocab pointer of llama-server when the --sleep-idle-seconds feature is enabled, allowing unauthenticated remote attackers to execute arbitrary code. Attackers can trigger the vulnerability by sending...

CVE-2026-43631: Use After Free

llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in the vocab pointer of llama-server when the --sleep-idle-seconds feature is enabled, allowing unauthenticated remote attackers to execute arbitrary code. Attackers can trigger the vulnerability by sending...

CVE-2026-43632: Use After Free

llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six tokenization endpoints /tokenize, /detokenize, /infill, /apply-template, /rerank, and /anthropic/counttokens that bypass the task queue and access ctxserver.vocab directly on HTTP...

PT-2026-68730

Name of the Vulnerable Software and Affected Versions llama.cpp versions b7492 through b9060 Description A use-after-free issue exists in the llama-server when the --sleep-idle-seconds feature is enabled. This occurs when the server transitions to sleep mode, causing concurrent worker threads to...

PT-2026-68731

Name of the Vulnerable Software and Affected Versions llama.cpp versions b7492 through b9060 Description A use-after-free issue exists in llama-server. This occurs when six tokenization endpoints—'/tokenize', '/detokenize', '/infill', '/apply-template', '/rerank', and '/anthropic/count...

CVE-2026-21869

llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the ndiscard parameter is parsed directly from JSON input in the llama.cpp server's completion endpoints without validation to ensure it's non-negative. When a negative value is supplied and the context fill...

CVE-2026-21869 llama.cpp has Out-of-bounds Write in llama-server

llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the ndiscard parameter is parsed directly from JSON input in the llama.cpp server's completion endpoints without validation to ensure it's non-negative. When a negative value is supplied and the context fill...