CVE-2025-71439 | 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.
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.
- 🔗 github.com/ggml-org/llama.cpp/security/advisories/GH…
- 🔗 github.com/ggml-org/llama.cpp/pull/14145
- 🔗 github.com/ggml-org/llama.cpp/commit/c33fe8b8c442720…
- 🔗 github.com/ggml-org/llama.cpp/blob/b5648/src/llama-v…
- 🔗 github.com/ggml-org/llama.cpp/releases/tag/b5649
- 🔗 www.vulncheck.com/advisories/llama-cpp-before-b5649-heap-ou…
Zero-Day & Vulnerability Intelligence Hub
Echtzeit-Tracking mit EPSS Exploit-Wahrscheinlichkeiten, Angriffsvektor-Decodern und KI-Patch-Anleitungen.
📊 Historien-Charts — Criticals-Trend · Vendors · EPSS-Verteilung
| Tier | CVEs | Anteil | Δ 7 T |
|---|---|---|---|
| ≥90 % | 792 | 0,2 % | +5 |
| ≥50 % | 3.564 | 0,9 % | +2 |
| ≥10 % | 13.173 | 3,2 % | +12 |
| <10 % | 397.352 | 95,8 % | +993 |
🗂️ …
CVE-2025-71439 | 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.
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