Medium
6.8
llama.cpp before b5649 Heap Out-of-Bounds Read via llama_vocab::impl::print_info
CVE-2025-71439
First seen on SecPulse
Affected packages
| Ecosystem | Package | Affected | Fixed |
|---|---|---|---|
| ggml-org | llama.cpp |
< b5649 |
b5649 |
Fix status by distribution
Fixed packages published by each distribution for this CVE
- Ubuntu UBUNTU-CVE-2025-71439 llama.cpp
Original description The description as published by the source.
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.
Source: CVE.org (CVE Program・cvelistV5) NVD GitHub Advisory
References
- advisory nvd.nist.gov
- advisory github.com
- web disclosure@vulncheck.com
- web disclosure@vulncheck.com
- web disclosure@vulncheck.com
- web disclosure@vulncheck.com
- web disclosure@vulncheck.com
- web disclosure@vulncheck.com
- web github.com