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.
Published:Oct 27, 2026
Last Modified:Oct 27, 2026
EPS:Oct 27, 2026
EPSS Score:
CVSS Score:5.5
Affected Products
Vendor
Product
Action
Vendor
Ggml
Product
Llama.cpp
Ggml
Llama.cpp
Vendor
Ggml-org
Product
Llama.cpp
Ggml-org
Llama.cpp
Exploits
No exploit reference
Common Weakness Enumeration
Common Attack Pattern Enumeration and Classification (CAPEC)
Related CVEs
References
Common Vulnerability Scoring System
Attack Vector
Network
Adjacent
Local
Physical
Privileges Required
None
Low
High
User Interaction
None
Required
Scope
Unchanged
Changed
Confidentiality
None
Low
High
Integrity
None
Low
High
Availability
None
Low
High
