CVE-2026-43631
Received Received - Intake

Remote Code Execution in llama.cpp via Use-After-Free

Vulnerability report for CVE-2026-43631, including description, CVSS score, EPSS score, affected products, exploitability, helpful resources, and attack-flow context.

Publication date: 2026-08-06

Last updated on: 2026-08-06

Assigner: VulnCheck

Description

llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in the vocab pointer of llama-server when the --sleep-idle-seconds feature is enabled, allowing unauthenticated remote attackers to execute arbitrary code. Attackers can trigger the vulnerability by sending requests to affected endpoints while the server transitions to sleep mode, causing concurrent worker threads to dereference a freed vocab pointer that can be reclaimed with attacker-controlled data to achieve remote code execution.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-08-06
Last Modified
2026-08-06
Generated
2026-08-07
AI Q&A
2026-08-07
EPSS Evaluated
N/A
NVD

Affected Vendors & Products

Currently, no data is known.

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-362 The product contains a concurrent code sequence that requires temporary, exclusive access to a shared resource, but a timing window exists in which the shared resource can be modified by another code sequence operating concurrently.
CWE-416 The product reuses or references memory after it has been freed. At some point afterward, the memory may be allocated again and saved in another pointer, while the original pointer references a location somewhere within the new allocation. Any operations using the original pointer are no longer valid because the memory "belongs" to the code that operates on the new pointer.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

This vulnerability is a use-after-free issue in llama.cpp versions b7492 through b9060. It occurs in the llama-server when the --sleep-idle-seconds feature is enabled. Attackers can exploit it by sending requests to endpoints while the server is transitioning to sleep mode, causing worker threads to dereference a freed vocab pointer. This pointer can be reclaimed with attacker-controlled data, leading to remote code execution.

Detection Guidance

Check if llama.cpp versions between b7492 and b9060 are running with --sleep-idle-seconds enabled. Inspect server logs for crashes or unexpected behavior during idle transitions. Monitor network traffic for suspicious requests targeting endpoints during sleep mode transitions.

Impact Analysis

If you are running a vulnerable version of llama.cpp with the --sleep-idle-seconds feature enabled, unauthenticated remote attackers could execute arbitrary code on your system. This could lead to complete compromise of the server, data theft, or further network infiltration.

Mitigation Strategies

Upgrade llama.cpp to a version beyond b9060 immediately. Disable the --sleep-idle-seconds feature if not required. Restrict network access to the llama-server to trusted sources only. Monitor for any signs of exploitation or unusual activity.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-43631. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart