Read the docs
TI-2025-43979 Aliases CVE-2025-71439GHSA-4qpr-vwfh-qwp4

Heap out-of-bounds read in llama.cpp crashes model loading

Priority MEDIUM 63CWE-125Published · Updated

Key facts

Attack vector
Local
Privileges required
None
User interaction
Passive
Attack complexity
Low
Attack requirements
None
Impact type
Denial of service
Confidentiality · integrity · availability
None · None · High
Fix status
Fixed

Attack profile from CVSS 4.0 · CNA. Fix status from CNA. Impact type from CWE-125 and the CVSS impact.

Summary

llama.cpp before b5649 contains a heap out-of-bounds read in llama_vocab::impl::print_info() (CWE-125). A local attacker can crash llama-cli or llama-server by supplying a crafted GGUF model with a short tokenizer.ggml.tokens array, so the program reads past id_to_token when a user loads the model.

Written with Claude Haiku 5.5 from the sources below · 2026-11-05

Description from the CNA

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.

Why it matters now

Exploitation Proof of concept CISA SSVC · not in CISA KEV
EPSS 0.00121 1st percentileScored 2026-11-07
Fix Fixed llama.cpp (ggml-org): b5649

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
Poc
Automatable
No
Technical impact
Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

VendorProductAffected versionsFixed inStatusSource
ggml-orgllama.cppbefore b5649b5649Patch availableCNA
  • llama.cpp Vendorggml-org Affected before b5649 Fixed in b5649 Patch available CNA

CPE names Threatist (inferred) · 1

Inferred from how NVD named this product before; not given by a source.

CPEVersionsRoleVendor
cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*——ggml-org
  • cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:* Versions — — ·ggml-org

Remediation

The fixed version for llama.cpp is b5649.

Written with Claude Haiku 5.5 from the sources below · 2026-11-05

  • Fix · CNA llama.cpp (ggml-org) Fixed in b5649

Timeline

  1. 2026-10-27 Threatist record created from CVE-2025-71439
  2. 2026-10-27 Alias added: GHSA-4qpr-vwfh-qwp4
  3. 2026-10-27 Priority changed: MEDIUM → LOW
  4. 2026-11-05 CISA SSVC decision points changed
  5. 2026-11-05 Priority changed: LOW → MEDIUM

References

Patch 2

Advisory 1

Other 2

  • TI-2026-26459 llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend CVSS 3.1CRITICAL 9.8
  • TI-2024-28446 llama.cpp allows Arbitrary Address Read in rpc_server::get_tensor CVSS 3.1CRITICAL 9.8
  • TI-2026-17570 llama.cpp has Out-of-bounds Write in llama-server CVSS 3.1CRITICAL 9.8
  • TI-2024-28447 llama.cpp allows write-what-where in rpc_server::set_tensor CVSS 3.1CRITICAL 10.0
  • TI-2024-15627 Integer overflow in ggml-org llama.cpp CVSS 3.1CRITICAL 9.8
  • TI-2024-14482 Heap-based buffer overflow in ggml-org llama.cpp CVSS 3.1CRITICAL 9.8
See all 52 →

Sources

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences