dbcve.org
Llama.cppApplication · Ggml

CVE-2024-42478

CRITICAL · 9.8 CVSS v3.1 Published 2024-08-12
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 provides LLM inference in C/C++. The unsafe `data` pointer member in the `rpc_tensor` structure can cause arbitrary address reading. This vulnerability is fixed in b3561.

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
How this class of weakness works · CWE-125

The code reads past the end (or before the start) of a buffer, returning memory that was never meant to be exposed. Attackers use it to leak secrets like keys or to defeat memory-protection defences. Remediation is validating indices and lengths before every read.

General guidance for the out-of-bounds read class — the official description and references above are authoritative for this specific CVE. Want a bespoke review and a reviewed fix? Ask our team →

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:< b3561

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

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 →
Recommended fix High confidence

b3561 or later

  1. Identify your current llama.cpp installation method (source build, package manager, or binary release)
  2. Backup any models, configurations, or custom build settings before upgrading
  3. Upgrade to llama.cpp version b3561 or later
  4. If building from source, pull the specific commit b3561 or a later tagged release
  5. Verify the upgrade by checking the installed version matches or exceeds b3561
  6. Test that your inference workloads function correctly after the upgrade
Caveat Review any RPC-related configuration changes if using distributed inference features, as the patch modifies the rpc_tensor structure

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

We can apply and verify the patch for your build — typical engagement from $3,550. Get the patch applied

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2024-42478 — 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-2024-42478 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