Read the docs
TI-2026-17570 Aliases CVE-2026-21869

llama.cpp has Out-of-bounds Write in llama-server

Priority HIGH 76CWE-787Published · Updated

Key facts

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

Attack profile from CVSS 3.1 · NVD. Fix status from CNA. Impact type from CWE-787 and the CVSS impact.

Summary

llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the n_discard parameter is parsed directly from JSON input in the llama.cpp server's completion endpoints without validation to ensure it's non-negative. When a negative value is supplied and the context fills up, llama_memory_seq_rm/add receives a reversed range and negative offset, causing out-of-bounds memory writes in the token evaluation loop. This deterministic memory corruption can crash the process or enable remote code execution (RCE). There is no fix at the time of publication.

Why it matters now

Exploitation Proof of concept CISA SSVC · not in CISA KEV
EPSS 0.00528 44th percentileScored 2026-11-07
Public exploit Yes 1 exploit referenceTagged by NVD
Fix No fix listed No fixed version in the sources yet

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
Poc
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.cppup to 55d4206c8—No fix listedCNA
  • llama.cpp Vendorggml-org Affected up to 55d4206c8 Fixed in — No fix listed CNA

CPE configurations NVD · 1

CPEVersionsRoleVendor
cpe:2.3:a:ggml:llama.cpp:-:*:*:*:*:*:*:*not specified by NVDVulnerableggml-org
  • cpe:2.3:a:ggml:llama.cpp:-:*:*:*:*:*:*:* Versions not specified by NVD Vulnerable ·ggml-org

Remediation

No fixed version listed by the sources yet.

Vendor assessments

Red Hat

Red Hat's page for this CVE →

Not affected: 1 product
  • Red Hat

Timeline

  1. 2026-10-02 Threatist record created from CVE-2026-21869

References

Exploit 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-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
  • TI-2025-32661 llama.cpp tokenizer signed vs. unsigned heap overflow CVSS 3.1HIGH 8.8
See all 28 →

Sources

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