TI-2026-82410 Aliases CVE-2026-119052 GHSA-rr32-94xq-hrxw

Uncaught exception in llama.cpp ggml-rpc server enables denial of service

MEDIUM 45CWE-248Published 2026-10-29 · Updated 2026-10-29

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 · High
Fix status: Fixed

Attack profile from CVSS 4.0 · CNA. Fix status from CNA. Impact type from CWE-248.

Summary

llama.cpp from b2877 before b11935 contains an uncaught exception in the ggml-rpc server. After the HELLO handshake, an unauthenticated remote attacker can send an oversized message length, such as in a SET_TENSOR command, which causes an uncaught std::length_error that aborts the process and denies service to all clients. The flaw is tracked as CWE-248 (Uncaught Exception).

Written with Claude Haiku 5.5 from the sources below · 2026-10-30

Description from the CNA

llama.cpp b2877 before b11935 contains an uncaught exception vulnerability in the ggml-rpc server that allows unauthenticated remote attackers to crash the rpc-server by sending oversized message lengths. After the HELLO handshake, attackers can send a command such as SET_TENSOR with a length above std::vector::max_size(), triggering an uncaught std::length_error that aborts the process and denies service to all clients.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV

EPSS 0.00613 49th percentileScored 2026-11-07

Fix Fixed llama.cpp (ggml-org): b11935

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	b2877 to before b11935	b11935	Patch available	CNA

llama.cpp Vendorggml-org Affected b2877 to before b11935 Fixed in b11935 Patch available CNA

CPE names Threatist (inferred) · 1

Inferred from how NVD named this product before; not given by a source.

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

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

Remediation

Upgrade llama.cpp to b11935 or later, which fixes the flaw. Red Hat lists one product as not affected.

Written with Claude Haiku 5.5 from the sources below · 2026-10-30

Fix · CNA llama.cpp (ggml-org) Fixed in b11935

Vendor assessments

Red Hat

Red Hat's page for this CVE →

Not affected: 1 product

Red Hat

Timeline

2026-10-29 Threatist record created from CVE-2026-119052
2026-10-29 Alias added: GHSA-rr32-94xq-hrxw
2026-10-29 CISA SSVC decision points changed
2026-10-30 Affected versions changed · Red Hat
2026-10-30 CVSS score added · Red Hat

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