Read the docs
TI-2026-31733 Aliases CVE-2026-43629GHSA-7p8h-8h8j-472c

llama.cpp b4882–b9058 Buffer Overflow in KV Cache State Restore

Priority MEDIUM 43CWE-190Published · Updated

Key facts

Attack vector
Network
Privileges required
None
User interaction
None
Attack complexity
Low
Attack requirements
Present
Impact type
Code execution
Confidentiality · integrity · availability
High · High · High
Fix status
No fix listed

Attack profile from CVSS 4.0 · CNA. Fix status from CNA and Red Hat. Impact type from CWE-190 and the CVSS impact.

Summary

llama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path where the state_read_data() function computes write size without overflow checking, allowing attackers with write access to the slot_save_path directory to corrupt heap memory. Attackers can craft malicious state files where cell_count multiplication overflows or exceeds tensor buffer allocation to write attacker-controlled bytes past buffer boundaries, potentially resulting in heap metadata corruption, model weight corruption, or arbitrary code execution via function pointer overwrite.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.00698 53rd percentileScored 2026-11-07
Fix No fix listed No fixed version in the sources yet

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.cppb4882 – b9058—No fix listedCNA
  • llama.cpp Vendorggml-org Affected b4882 – b9058 Fixed in — No fix listed CNA

CPE configurations NVD · 1

CPEVersionsRoleVendor
cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*b4882 – b9058Vulnerableggml-org
  • cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:* Versions b4882 – b9058 Vulnerable ·ggml-org

Remediation

No fixed version listed by the sources yet.

Vendor assessments

Red Hat

Red Hat rating: Important. Red Hat's page for this CVE →

ProductStatusPlan or fix
Red Hat Enterprise Linux AI (RHEL AI) 3AffectedNo fix yet

Timeline

  1. 2026-10-02 Threatist record created from CVE-2026-43629
  2. 2026-10-03 Alias added: GHSA-7p8h-8h8j-472c
  3. 2026-10-29 Affected versions changed · CNA

References

Patch 1

  • 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 28 →

Sources

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