Read the docs
TI-2026-81006 Aliases CVE-2026-116840GHSA-52pf-v9gp-98qj

Integer overflow in llama.cpp GGUF reader enables out-of-bounds reads

Priority LOW 29CWE-190Published · Updated

Key facts

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

Attack profile from CVSS 4.0 · CNA. Fix status from CNA.

Summary

llama.cpp from b5854 before b11275 contains an integer overflow in gguf_init_from_reader that bypasses the size check added for CVE-2025-53630 when padding near-SIZE_MAX tensor sizes. A crafted GGUF file whose tensor size pads to zero creates an undersized data blob, so consumers perform out-of-bounds reads. An attacker needs local access and must get a user to load the crafted file. The flaw is tracked as CWE-190.

Written with Claude Haiku 5.5 from the sources below · 2026-10-28

Description from the CNA

llama.cpp b5854 before b11275 contains an integer overflow vulnerability in gguf_init_from_reader that bypasses the CVE-2025-53630 size check when padding near-SIZE_MAX tensor sizes. Attackers can supply a crafted GGUF file whose tensor size pads to zero, causing an undersized data blob and out-of-bounds reads by consumers.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.00126 2nd percentileScored 2026-11-07
Fix Fixed llama.cpp (ggml-org): b11275, 0.6.0

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
None
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.cppb5854 to before b11275; 0.1.0 to before 0.6.0b11275, 0.6.0Patch availableCNA
  • llama.cpp Vendorggml-org Affected b5854 to before b11275; 0.1.0 to before 0.6.0 Fixed in b11275, 0.6.0 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 b11275 or later for the b5854 line, and to 0.6.0 or later for the 0.1.0 line.

Written with Claude Haiku 5.5 from the sources below · 2026-10-28

  • Fix · CNA llama.cpp (ggml-org) Fixed in b11275, 0.6.0

Timeline

  1. 2026-10-27 Threatist record created from CVE-2026-116840
  2. 2026-10-27 CISA SSVC decision points changed
  3. 2026-10-27 Priority changed: MEDIUM → LOW
  4. 2026-10-27 Alias added: GHSA-52pf-v9gp-98qj

References

Patch 2

Other 3

  • 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