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.
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
- Feb 26, 2024CVE publishedPublication date reported by the CVE source.
- 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.
- Affected versionversion=18c2e17
- Affected versionversion=Commit 18c2e17
What conditions does exploitation require?
What is affected?
Published CVSS scores
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.
Weakness, pattern, technique
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