CVE-2024-21836Network attack vector

Code execution via tensor-count allocation overflow

Published Feb 26, 2024 · Updated Nov 4, 2025

Heap buffer overflow in llama.cpp commit 18c2e17 allows attackers to execute code when a crafted GGUF model file is loaded. gguf_init_from_file multiplies the untrusted header.n_tensors value by the 88-byte tensor-info size without checking for integer overflow, underallocating ctx->infos before gguf_fread_str writes through an out-of-bounds element. User interaction is required to load the file, after which memory corruption can crash the process or enable code execution.

CVSS severity8.8
High
EPSS probability1.35%
Next 30 days · Sep 16, 2026
Known exploitationUnconfirmed
Based on sourced intelligence
Hinoki checkNot available
Coverage for this vulnerability

See if you're affected

Explore vulnerability checks for your environment with Hinoki.

Book a demo

Summary

What happened

Heap buffer overflow in llama.cpp commit 18c2e17 allows attackers to execute code when a crafted GGUF model file is loaded. gguf_init_from_file multiplies the untrusted header.n_tensors value by the 88-byte tensor-info size without checking for integer overflow, underallocating ctx->infos before gguf_fread_str writes through an out-of-bounds element. User interaction is required to load the file, after which memory corruption can crash the process or enable code execution.

The record

CVE
CVE-2024-21836
Published
Feb 26, 2024
Updated
Nov 4, 2025
Vendor
Georgi Gerganov
Product
llama.cpp
Classifications
CWE-190, T1204.002, T1203
Attack vector
network
Privileges
unauthenticated

Timeline

How it unfolded

  1. Feb 26, 2024CVE publishedPublication date reported by the CVE source.
  2. Nov 4, 2025Record updatedLatest update available in the CVE record.

Exploitability

Present is not the same as exploitable

Compare your product and version with the public record. A matching version still requires validation against your environment.

Is a vulnerable build present?

Compare these published version ranges with your installed build and any vendor patches.

  1. Affected versionversion=18c2e17
  2. Affected versionversion=Commit 18c2e17

What conditions does exploitation require?

Attack vectornetwork
Required privilegesunauthenticated

What is affected?

Georgi Gerganov · llama.cppversion=18c2e17; version=Commit 18c2e17

Published CVSS scores

8.8Cisco TalosCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

CVSS describes severity. EPSS estimates exploitation probability.

Attacks

What attackers are doing with it

Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.

Daily unique IPsNo honeypot observations are available for this CVE in the selected window.

No observations available

Sep 10, 2026Sep 16, 2026
Latest reporting daySep 16, 2026
Latest daily unique IPsUnavailable
Prior 30-day averageUnavailable
SourceShadowserver honeypots (KEV)
Vectornetwork
Privilegesunauthenticated
Known exploitationUnconfirmed
Public exploitUnconfirmed

Weakness, pattern, technique

CWE-190Integer Overflow or Wraparound
T1204.002User Execution Malicious File
T1203Exploitation for Client Execution

Public exploit references

No public exploit references are available in this record.

Labels summarize the accepted research assessment. They do not indicate a test against your environment.

Technologies

Your stack

See the directory against your own environment.

Your stack

Check the software in your environment

Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.

Book a demo