Read the docs
TI-2026-81000 Aliases CVE-2026-116816GHSA-3r8c-j789-2864

llama.cpp Heap Out-of-Bounds Write via plamo2 Tokenizer

Priority LOW 38CWE-129Published · Updated

Key facts

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

Attack profile from CVSS 4.0 · CNA. Fix status from CNA. Impact type from CWE-129 and the CVSS impact.

Summary

llama.cpp from b5899 before b10261 contains a heap out-of-bounds write in the plamo2 tokenizer's build routine. A missing index check (CWE-129) lets a negative token id from a crafted GGUF model write data before the bytes buffer during model loading. An attacker who supplies a crafted model file can corrupt heap memory, causing crashes or potentially code execution, and exploitation requires user interaction.

Written with Claude Haiku 5.5 from the sources below · 2026-10-31

Description from the CNA

llama.cpp b5899 before b10261 contains a heap out-of-bounds write vulnerability in llm_tokenizer_plamo2::build that allows attackers to corrupt heap memory via crafted GGUF models. Attackers can supply BYTE-typed token text like <0x-1> whose negative parsed value writes token ids before the bytes_ buffer during model loading, causing crashes or potential code execution.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.00135 2nd percentileScored 2026-11-07
Fix Fixed llama.cpp (ggml-org): b10261

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
None
Automatable
No
Technical impact
Total

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.cppb5899 to before b10261b10261Patch availableCNA
  • llama.cpp Vendorggml-org Affected b5899 to before b10261 Fixed in b10261 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

Update llama.cpp to b10261 or later.

Written with Claude Haiku 5.5 from the sources below · 2026-10-31

  • Fix · CNA llama.cpp (ggml-org) Fixed in b10261

Timeline

  1. 2026-10-27 Threatist record created from CVE-2026-116816
  2. 2026-10-27 Alias added: GHSA-3r8c-j789-2864
  3. 2026-10-27 Priority changed: MEDIUM → LOW
  4. 2026-10-31 CISA SSVC decision points changed

References

Patch 3

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