CVE-2025-71439

CVSS 6.8 (medium) · published 2026-10-27

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.

Weakness: CWE-125

Source: NVD CVE-2025-71439

References

• https://github.com/ggml-org/llama.cpp/blob/b5648/src/llama-vocab.cpp#L2771
• https://github.com/ggml-org/llama.cpp/commit/c33fe8b8c4427202706b1434e9fc8ab5752c9cac
• https://github.com/ggml-org/llama.cpp/pull/14145
• https://github.com/ggml-org/llama.cpp/releases/tag/b5649
• https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-g4cc-763q-h9h6
• https://www.vulncheck.com/advisories/llama-cpp-before-b5649-heap-out-of-bounds-read-via-llama-vocab-impl-print-info
• https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-g4cc-763q-h9h6

Check your software

Connect an AI agent to the FixLane MCP server or ask the Telegram bot to check what you have installed against incidents with a verified fixed version.