Live › vulnerability › CVE-2024-58400
Go to dashboardllama.cpp before b3701 does not validate token IDs in llama_decode_internal and llama_encode_internal, so an out-of-range ID reads memory outside the embedding table. A remote unauthenticated attacker sending integer-array prompts to the llama-server /completion endpoint can read process memory or crash the server.
Summary written from the sources below. Check the originals before acting.
First seen by InfraStack 2026-10-27 01:34 UTC. All times on this page are UTC.
Teams that run llama-server from llama.cpp and expose its HTTP API to clients beyond the host, since the /completion endpoint accepts raw integer-array token prompts from any caller. Local-only use behind authentication or with no network exposure is lower risk. Teams using llama.cpp only as a library with no server exposed can skip the server-specific checks.
No product ranges from the sources yet.
llama-server --version or check the build tag on the host; anything older than b3701 is affected.b3701 or later and rebuild llama-server.Each row is the first time that source carried this signal. The analyst’s rows are its own findings.
llama.cpp before b3701 contains an out-of-bounds read vulnerability in llama_decode_internal and llama_encode_internal that allows remote unauthenticated attackers to read memory by supplying unvalidated token IDs. Attackers can send integer-array prompts to the llama-server /completion endpoint with IDs outside 0 to n_vocab to read embedding memory out of bounds or crash the process.
This page as .md · .json · in your agent: get_signal("CVE-2024-58400")
NVD data is provided by NIST and is public domain. Posts quoted belong to their authors.