dbcve.org
Llama.cppApplication · Ggml

CVE-2024-32878

HIGH · 8.8 CVSS v3.1 Published 2024-04-26
Mitigation only
No fix yet — a mitigation exists. There is no fixed release. A documented workaround reduces exposure in the meantime.
See remediation →
95/100
Remediation priority · Urgent
Remotely reachable No privileges

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 LLM inference in C/C++. There is a use of uninitialized heap variable vulnerability in gguf_init_from_file, the code will free this uninitialized variable later. In a simple POC, it will directly cause a crash. If the file is carefully constructed, it may be possible to control this uninitialized value and cause arbitrary address free problems. This may further lead to be exploited. Causes llama.cpp to crash (DoS) and may even lead to arbitrary code execution (RCE). This vulnerability has been patched in commit b2740.

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 contains a use of uninitialized heap variable vulnerability in the gguf_init_from_file function. The function allocates memory but fails to initialize it properly before the code later attempts to free this uninitialized pointer. In simple cases this causes an immediate crash (DoS), but a crafted GGUF file can control the uninitialized value leading to arbitrary address free and potentially RCE.

MitigationUpgrade to the version containing commit b2740 or later. If immediate patching is not possible, avoid processing GGUF files from untrusted sources until the update is 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:>= b2715, < b2740

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
Required
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

CVSS:3.1/AV:N/AC:L/PR:N/UI:R/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
    Run 'llama-cli --version' or 'llama-parse --version' or check the library file (libgguf.so/libgguf.a) for version metadata. If built from source, check the commit hash shown in the build output or 'git log'.
    Affected if The version/commit is >= b2715 and < b2740 (or the commit hash falls between these build numbers).
  2. Verify GGUF file processing capability
    Check if the installed binary or linked library has GGUF parsing enabled. Look for 'gguf_init_from_file' in the binary symbols: 'nm -D libgguf.so 2>/dev/null | grep gguf_init_from_file' or 'strings binary | grep gguf'.
    Affected if The gguf_init_from_file function is present and accessible in the installed binary or library.
  3. Confirm active GGUF file usage
    Review application logs, processes, or configurations that load GGUF files (common in LLM applications using llama.cpp). Check for recently opened or processed .gguf model files.
    Affected if The system actively processes GGUF files, especially from external or untrusted sources.

A system is affected if it runs a llama.cpp version with build/commit number b2715 through b2740 and processes GGUF files.

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
Mitigation available No clean upgrade yet — mitigate in the meantime
Mitigation

Upgrade to the version containing commit b2740 or later. If immediate patching is not possible, avoid processing GGUF files from untrusted sources until the update is applied.

Recommended fix High confidence

Update to any llama.cpp version/commit after b2740 (the fix is in commit b2740)

  1. 1. Identify the current llama.cpp version in use by checking the build version or git commit hash
  2. 2. Verify the current version is >= b2715 and < b2740 (or not sure of version, proceed with upgrade)
  3. 3. Update to a version of llama.cpp that includes commit b2740 or later
  4. 4. Rebuild/recompile the application with the updated llama.cpp source
  5. 5. Test the application to verify it no longer crashes when parsing GGUF files
  6. 6. If using llama.cpp as a library, ensure any dependent applications are also rebuilt against the fixed version

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

Fix this in Llama.cpp Scoped from the published advisory
  • Consultation3.0 h
  • Implementation6.0 h
  • Testing4.0 h
  • Review / QA2.0 h
15.0 hours of engineering $2,640
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $4,224.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2024-32878 — 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-2024-32878 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