Read the docs
TI-2024-39151 Aliases CVE-2024-58399GHSA-xf8w-pfxh-7xj3

llama.cpp Out-of-Bounds Read via Crafted GGUF Tensor Offsets

Priority LOW 29CWE-125Published · 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 b1046 before b2731 contains an out-of-bounds read (CWE-125) in llama_model_loader. A crafted or truncated GGUF model file with arbitrary 64-bit tensor offsets lets an attacker read memory outside the mapped model file. An attacker who gets a victim to load such a model can crash the process or load adjacent process memory as model weights.

Written with Claude Haiku 5.5 from the sources below · 2026-11-02

Description from the CNA

llama.cpp before b2731 contains an out-of-bounds read vulnerability in llama_model_loader that allows attackers to read memory outside the mapped model file via crafted GGUF tensor offsets. Attackers can supply a crafted or truncated GGUF model file with arbitrary 64-bit tensor offsets to crash the process or load adjacent process memory as model weights.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.0012 1st percentileScored 2026-11-07
Fix Fixed llama.cpp (ggml-org): b2731

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.cppb1046 to before b2731b2731Patch availableCNA
  • llama.cpp Vendorggml-org Affected b1046 to before b2731 Fixed in b2731 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 b2731 or later, the first fixed version listed for ggml-org llama.cpp.

Written with Claude Haiku 5.5 from the sources below · 2026-11-02

  • Fix · CNA llama.cpp (ggml-org) Fixed in b2731

Timeline

  1. 2026-10-27 Threatist record created from CVE-2024-58399
  2. 2026-10-27 Alias added: GHSA-xf8w-pfxh-7xj3
  3. 2026-10-27 Priority changed: MEDIUM → LOW
  4. 2026-11-02 CISA SSVC decision points changed

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