TI-2026-80547 Aliases CVE-2026-116467 GHSA-qh3g-v296-6ghm

Reachable assertion in ggml-org llama.cpp Mirostat sampler

LOW 37CWE-617Published 2026-10-26 · Updated 2026-10-26

Key facts

Attack vector: Network
Privileges required: None
User interaction: None
Attack complexity: Low
Attack requirements: None
Impact type: Denial of service
Confidentiality · integrity · availability: None · None · Low
Fix status: No fix listed

Attack profile from CVSS 4.0 · CNA. Fix status from CNA. Impact type from CWE-617.

Summary

ggml-org llama.cpp up to 0.7.0 is affected. A reachable assertion in the Mirostat Sampler component of src/llama-sampler.cpp lets crafted input crash the process (CWE-617). A remote attacker without privileges or user interaction can trigger it, with a low availability impact. The project was informed through a pull request but has not responded.

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

Description from the CNA

A security flaw has been discovered in ggml-org llama.cpp up to 0.7.0. Affected by this vulnerability is an unknown functionality of the file src/llama-sampler.cpp of the component Mirostat Sampler. The manipulation results in reachable assertion. It is possible to launch the attack remotely. The project was informed of the problem early through a pull request but has not reacted yet.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV

EPSS 0.00638 50th 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: Yes
Technical impact: Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

Vendor	Product	Affected versions	Fixed in	Status	Source
ggml-org	llama.cpp	0.1; 0.2; 0.3; 0.4; 0.5; 0.6; 0.7.0	—	No fix listed	CNA

llama.cpp Vendorggml-org Affected 0.1; 0.2; 0.3; 0.4; 0.5; 0.6; 0.7.0 Fixed in — No fix listed CNA

CPE names CNA · 1

CPE	Versions	Role	Vendor
cpe:2.3:a:ggml-org:llama.cpp::::::::	—	—	—

cpe:2.3:a:ggml-org:llama.cpp:*:*:*:*:*:*:*:* Versions — — ·—

Remediation

The sources list no fixed version for llama.cpp.

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

Timeline

2026-10-26 Threatist record created from CVE-2026-116467
2026-10-26 CISA SSVC decision points changed
2026-10-26 Priority changed: MEDIUM → LOW
2026-10-27 Alias added: GHSA-qh3g-v296-6ghm

References

Patch 1

https://github.com/ggml-org/llama.cpp/pull/29992

Other 1

https://github.com/ggml-org/llama.cpp/

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