https://db.gcve.eu/rss/recent/all/10 Most recent entries from all 2026-10-27T17:44:55.450506+00:00 Vulnerability-Lookup info@gcve.eu python-feedgen Contains only the most 10 recent entries. https://db.gcve.eu/vuln/fkie_cve-2025-71439 fkie_cve-2025-71439 2026-10-27T17:44:55.477038+00:00

llama.cpp before b5649 contains a heap out-of-bounds read vulnerability in llama_vocab::impl::print_info() that allows attackers to crash model loading via oversized special token IDs. Attackers can supply a crafted GGUF model with a short tokenizer.ggml.tokens array, causing llama-cli or llama-server to read past id_to_token and crash.

 https://db.gcve.eu/vuln/ghsa-4qpr-vwfh-qwp4 GHSA-4qpr-vwfh-qwp4 2026-10-27T17:44:55.477126+00:00

llama.cpp before b5649 contains a heap out-of-bounds read vulnerability in llama_vocab::impl::print_info() that allows attackers to crash model loading via oversized special token IDs. Attackers can supply a crafted GGUF model with a short tokenizer.ggml.tokens array, causing llama-cli or llama-server to read past id_to_token and crash.