Code execution via unchecked allocation-size multiplication
Published Aug 6, 2026 · Updated Aug 6, 2026
Integer overflow in llama_batch_init() in llama.cpp b1283 through b9058 allows local users to execute code via oversized batch parameters. The function multiplies attacker-influenced token, embedding, and sequence counts in malloc size expressions without first checking for size_t overflow. Exploitation requires a user or local process to run an inference workload with maliciously oversized batch values; bounded or fixed server parameters prevent reachability.
Summary
What happened
Integer overflow in llama_batch_init() in llama.cpp b1283 through b9058 allows local users to execute code via oversized batch parameters. The function multiplies attacker-influenced token, embedding, and sequence counts in malloc size expressions without first checking for size_t overflow. Exploitation requires a user or local process to run an inference workload with maliciously oversized batch values; bounded or fixed server parameters prevent reachability.
The record
- CVE
- CVE-2026-43627
- Published
- Aug 6, 2026
- Updated
- Aug 6, 2026
- Vendor
- Georgi Gerganov
- Product
- llama.cpp
- Classifications
- Unavailable
- Attack vector
- local
- Privileges
- authenticated
Timeline
How it unfolded
- Aug 6, 2026CVE publishedPublication date reported by the CVE source.
- Aug 6, 2026Record 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=0.4.0 <=0.17.1
- Affected versionversion=b1283 <=b9058
What conditions does exploitation require?
What is affected?
Published CVSS scores
No CVSS assessment is available in this record.
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
No sourced classifications are available.
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