Server crash and sampling corruption via DRY underflow
Published Aug 6, 2026 · Updated Aug 6, 2026
Integer underflow in the DRY sampler in ggml.ai llama.cpp 0.11.0 through 0.17.1 allows remote attackers to crash its server. The server accepts a negative dry_allowed_length from completion JSON and passes it into DRY sampling without a nonnegative bounds check, causing reads before the heap buffer. Unauthenticated access to a completion endpoint is sufficient; the read can terminate the process or distort token-sampling probabilities with unrelated memory values.
Summary
What happened
Integer underflow in the DRY sampler in ggml.ai llama.cpp 0.11.0 through 0.17.1 allows remote attackers to crash its server. The server accepts a negative dry_allowed_length from completion JSON and passes it into DRY sampling without a nonnegative bounds check, causing reads before the heap buffer. Unauthenticated access to a completion endpoint is sufficient; the read can terminate the process or distort token-sampling probabilities with unrelated memory values.
The record
- CVE
- CVE-2026-43628
- Published
- Aug 6, 2026
- Updated
- Aug 6, 2026
- Vendor
- Georgi Gerganov
- Product
- llama.cpp
- Classifications
- CWE-191, CWE-125, T1499
- Attack vector
- network
- Privileges
- unauthenticated
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=0.11.0 <=0.17.1
- Affected versionversion=b3978 <=b9058
What conditions does exploitation require?
What is affected?
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