llama.cpp builds b3978 through b9058 contain an integer underflow and out-of-bounds read vulnerability in the DRY sampler that allows unauthenticated attackers to trigger a heap buffer underflow by sending a crafted HTTP request with dry_allowed_length set to INT32_MIN to the /v1/completions or /v1/chat/completions endpoints. Attackers can exploit this vulnerability to crash the server with SIGSEGV causing denial of service for all connected users, or corrupt token sampling probabilities by reading garbage values from memory before the allocated buffer.

Attack Vector Local

Attack Complexity Low

Privileges Required None

Attack Requirements None

User Interaction Passive

Vulnerable System Confidentiality Impact High

Vulnerable System Integrity Impact High

Vulnerable System Availability Impact High

Subsequent System Confidentiality Impact None

Subsequent System Integrity Impact None

Subsequent System Availability Impact None

Attack Vector Local

Attack Complexity Low

Privileges Required None

Scope Unchanged

Confidentiality Impact High

Integrity Impact High

Availability Impact High

User Interaction Required

No CVSS v3.0

No CVSS v2

This CVE is not in the KEV list.

No EPSS score available.

Key SSVC decision points have not yet been added.

Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).

Vendor Product Default status Versions
ggml-org llama.cpp affected
Version Status Constraints
b3978 affected ≤ b9058
0.11.0 affected ≤ 0.17.1

No data.

No data.

OpenCVE Enrichment is a feature of OpenCVE that uses AI to automatically link vendors and products to CVEs. Learn more on GitHub.

Vendors Products
Ggml-org Subscribe
Llama.cpp Subscribe

Project Subscriptions

Vendors Products
Ggml-org Subscribe
Llama.cpp Subscribe
Advisories

No advisories yet.

Fixes

Solution

No solution given by the vendor.

Workaround

No workaround given by the vendor.

References
Link Providers
https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches cve-icon
History

Fri, 07 Aug 2026 02:15:00 +0000

Type Values Removed Values Added
First Time appeared Ggml-org
Ggml-org llama.cpp
Vendors & Products Ggml-org
Ggml-org llama.cpp

Thu, 06 Aug 2026 22:15:00 +0000

Type Values Removed Values Added
Description llama.cpp builds b3978 through b9058 contain an integer underflow and out-of-bounds read vulnerability in the DRY sampler that allows unauthenticated attackers to trigger a heap buffer underflow by sending a crafted HTTP request with dry_allowed_length set to INT32_MIN to the /v1/completions or /v1/chat/completions endpoints. Attackers can exploit this vulnerability to crash the server with SIGSEGV causing denial of service for all connected users, or corrupt token sampling probabilities by reading garbage values from memory before the allocated buffer.
Title llama.cpp b3978–b9058 Integer Underflow via DRY Sampler
Weaknesses CWE-125
CWE-191
References
Metrics cvssV3_1

{'score': 7.8, 'vector': 'CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H'}

cvssV4_0

{'score': 8.5, 'vector': 'CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N'}

Projects

Sign in to view the affected projects.

cve-icon MITRE

Status: PUBLISHED

Assigner: VulnCheck

Published:

Updated: 2026-08-06T15:45:52.293Z

Reserved: 2026-05-01T18:22:45.641Z

Link: CVE-2026-43628

cve-icon Vulnrichment

No data.

cve-icon NVD

No data.

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

Updated: 2026-08-07T02:15:04Z

Weaknesses