ZDF
Sign inSign up

Vulnerabilities

Vulnerability · CVE-2026-33298

llama.cpp is an inference of several LLM models in C/C++.

Published Mar 24, 2026 · catalog updated Jun 17, 2026 · llama.cpp is an inference

Check if you run it

No confirmed exploitation is on record for CVE-2026-33298. EPSS is 0.37%. Act only if a listed version of llama.cpp is an inference is installed.

Gaps on this record

  • The stored product name is a package slug. The name on this page is taken from the title (llama.cpp is an inference).
  • No version range is stored. A customer cannot check an installed version against this record.
  • No vendor fix or required action is stored. Compare the linked advisory before you change production.
Severity
High7.8
Known exploitation
Not in CISA/VulnCheck KEV
EPSS
0.37%
Remediation
Advisory link
Affected products
cpe ggml/llama.cpp

llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes to return a significantly smaller size than required (e.g., 4MB instead of Exabytes), leading to a heap-based buffer overflow when the application subsequently processes the tensor. This vulnerability allows potential Remote Code Execution (RCE) via memory corruption. b7824 contains a fix.

Are you affected?

Enter the version you run. The result uses only the ranges stored on this record.

The check returns affected, not affected, or incomplete. It does not guess a version that is missing from the record.

  • cpe ggml/llama.cppversion unspecified

How to fix CVE-2026-33298

What to do

Three questions, each answered from this record only. Confirm the vendor advisory before you patch.

Should you patch?

No confirmed exploitation is on record for CVE-2026-33298. EPSS is 0.37%. Act only if a listed version of llama.cpp is an inference is installed.

Which versions are affected?

Affected version ranges are not on this record. Compare the installed version with the linked vendor advisory before you change production.

What should an analyst verify?

CWE-122: Heap-based Buffer Overflow; CWE-190: Integer Overflow. EPSS 0.37%. There is no CISA KEV listing. No Exploit-DB or Metasploit reference is linked. Use the source links for the original advisory.

Code

The project this record applies to. Exploit listings stay in References.

Timeline

Detection, updates, and resolution for this record.

  1. Mar 24, 2026 · NIST NVD

    Detected

    llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes to return a significantly smaller size than required (e.g., 4MB instead of Exabytes), leading to a heap-based buffer overflow when the application subsequently

  2. Jun 17, 2026 · NIST NVD

    Updated

    llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes to return a significantly smaller size than required (e.g., 4MB instead of Exabytes), leading to a heap-based buffer overflow when the application subsequently

Sources

  • CVE.orgVulnerability recordCVE-2026-33298

    Official CVE identifier

    cve.org
  • FIRST EPSSExploitation probabilityCVE-2026-33298

    30-day exploitation probability 0.4%

    first.org
  • NIST NVDVulnerability recordCVE-2026-33298

    llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes to return a

    nvd.nist.gov

References

Freshness

Last verified in this catalog Oct 18, 2026. Significant claims (KEV, EPSS, CVSS, affected ranges) come from the source rows above — open the original publisher for the authoritative advisory.