| Package | Affected versions | Patched versions |
|---|---|---|
| No affected product versions are listed for this vulnerability yet. | ||
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.
Running one of these products? Scan your site to see whether it exposes a vulnerable version.
Scan my site free