CVE-2025-71439

llama.cpp before b5649 Heap Out-of-Bounds Read via llama_vocab::impl::print_info

Published Oct 27, 2026 CVSS 4.0 · 6.8 Medium EPSS < 1% KEV · Not listed
Description
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.

Analysis

AI-generated

Technical impact

llama.cpp before commit b5649 contains a heap out‑of‑bounds read in llama_vocab::impl::print_info. An attacker can craft a GGUF model with a short tokenizer.ggml.tokens array that causes the function to read beyond the allocated memory when loading the model. The out‑of‑bounds read results in a crash of llama‑cli or llama‑server, effectively denying service for the model loading operation.

Affected Systems

All installations of the ggml‑org/llama.cpp library that use llama‑cli or llama‑server to load GGUF model files are affected if they are built from any revision prior to the b5649 commit referenced in the advisory. This includes every release before that commit, since the vulnerability lies in the core vocabulary handling code.

Risk and Exploitability

The CVSS score of 6.8 indicates medium severity. EPSS data is not available, and the vulnerability is not listed in the CISA KEV catalog, suggesting that exploitation is not widely observed. Attackers can trigger the effect by supplying a malicious GGUF model file; the attack vector is the model file distribution or local model loading. The primary impact is service disruption due to a crash, with no disclosed disclosure of memory contents.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Upgrade llama.cpp to version b5649 or newer, which removes the out-of-bounds read in print_info.
  • If an upgrade is unavoidable in the short term, validate any GGUF model before loading by checking that the tokenizer.ggml.tokens array is sufficiently large to prevent the crash.
  • Restrict model loading to trusted sources or enforce a model integrity check that rejects malformed or malicious GGUF files until the patch is available.

Generated by OpenCVE AI on October 27, 2026 at 07:44 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories available
History
Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'poc', 'Technical Impact': 'partial'}, 'version': '2.0.3'}

Type Values Removed Values Added
First Time appeared Ggml-org
Ggml-org llama.cpp
Vendors & Products Ggml-org
Ggml-org llama.cpp
Type Values Removed Values Added
Description 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.
Title llama.cpp before b5649 Heap Out-of-Bounds Read via llama_vocab::impl::print_info
First Time appeared Ggml
Ggml llama.cpp
Weaknesses CWE-125
CPEs cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*
Vendors & Products Ggml
Ggml llama.cpp
References
Metrics cvssV3_1

{'score': 5.5, 'vector': 'CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H'}

cvssV4_0

{'score': 6.8, 'vector': 'CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N'}

Weaknesses

Sources

Status
PUBLISHED
Assigner
VulnCheck
Published
Updated
Nov 5, 2026, 3:22 PM
Reserved
Oct 27, 2026, 12:10 AM
Status
Awaiting Analysis
Published
Oct 27, 2026, 1:19 AM
Modified
Nov 5, 2026, 4:17 PM