dbcve.org
Llama.cppApplication · Ggml

CVE-2026-34159

CRITICAL · 9.8 CVSS v3.1 Published 2026-04-01
Patch available
A vendor patch is available. No clean upgrade release — apply the published patch.
See remediation →
100/100
Remediation priority · Urgent
Public exploit Remotely reachable No privileges Zero-click Patch available

Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.

NVD · unedited
llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserialize_tensor() skips all bounds validation when a tensor's buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPH_COMPUTE messages. Combined with pointer leaks from ALLOC_BUFFER/BUFFER_GET_BASE, this gives full ASLR bypass and remote code execution. No authentication required, just TCP access to the RPC server port. This issue has been patched in version b8492.

Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.

dbcve analysis · high confidence

llama.cpp's RPC backend contains a critical memory corruption vulnerability in deserialize_tensor() which skips all bounds validation when a tensor's buffer field equals 0. An unauthenticated attacker with network access to the RPC server can send crafted GRAPH_COMPUTE messages to achieve arbitrary memory read/write, and combined with pointer leaks from ALLOC_BUFFER/BUFFER_GET_BASE, can bypass ASLR and achieve remote code execution.

MitigationUpgrade llama.cpp to version b8492 or later. As an interim control, restrict network access to the RPC server port using firewall rules or network segmentation until the patch can be applied.

Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.

Affected products & versions What the vendor confirmedThe version ranges the vendor confirmed as vulnerable. If your version sits inside a range here, treat yourself as exposed until you have upgraded.

NVD · CPE data
Llama.cppApplication
Affected:< b8492

CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.

From the vector
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.

dbcve checks

Work through these to decide whether this CVE applies to you.

  1. Identify installed llama.cpp version
    Locate the llama.cpp binary or library in your environment and retrieve its version (for example, via --version flag, binary metadata, or package manager query). Compare the version to b8492 - versions below b8492 are affected.
    Affected if Installed version is lower than b8492
  2. Verify RPC server is enabled
    Check if the llama.cpp RPC server component is running or configured to run. Look for RPC-related configuration files, running processes, or service definitions related to llama.cpp.
    Affected if RPC server component is active or configured to run
  3. Confirm network exposure of RPC port
    Inspect network listener configurations or firewall rules to determine if the RPC server port is bound to a network-accessible interface (as opposed to localhost-only). Use netstat, ss, or similar tools to identify listening ports associated with llama.cpp.
    Affected if RPC server port is exposed to network interfaces other than localhost

All three conditions must be true for the environment to be affected: llama.cpp version below b8492, RPC server is enabled, and the RPC port is network-accessible.

Generated from the published advisory. Verify against your own configuration.

Check your environment

Paste your version and any relevant configuration and it will be compared against the affected criteria above. Do not include secrets or credentials.

AI-assisted, checked against the advisory. Informational, not a guarantee.

Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.

dbcve · scoped
Patch available Apply the vendor patch
Vendor patch github.com →
Interim mitigation

Upgrade llama.cpp to version b8492 or later. As an interim control, restrict network access to the RPC server port using firewall rules or network segmentation until the patch can be applied.

Recommended fix High confidence

llama.cpp version b8492 or later

  1. 1. Identify the current version of llama.cpp running the RPC server by checking the binary or build information
  2. 2. Stop the llama.cpp RPC server if it is currently running
  3. 3. Download or build llama.cpp version b8492 or later from the official repository (https://github.com/ggml-org/llama.cpp)
  4. 4. Replace the existing llama.cpp binary with the updated version
  5. 5. Restart the RPC server with the patched binary
  6. 6. Verify the server is running the patched version and the RPC functionality works correctly
Caveat Review release notes between current version and b8492 for any breaking changes in RPC protocol or other functionality

Generated from the published advisory — verify against the referenced sources before acting.

Fix this in Llama.cpp Scoped from the published advisory
  • Consultation4.0 h
  • Implementation8.0 h
  • Testing4.0 h
  • Review / QA2.0 h
18.0 hours of engineering $3,200
Get the patch applied

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $5,120.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-34159 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

Get it on GitHub Scan in the browser

References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.

Primary sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2026-34159 in production — separate from our analysis above.

No notes yet

Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.

What this is

A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.

What belongs here
  • Verified mitigations, workarounds, and config changes
  • Version or environment caveats, and links to real fixes
  • No weaponised exploit code, or anything meant to cause harm
  • No spam, self-promotion, credentials, or personal data