Process crash via invalid model ftype assertion
Published Jul 27, 2026 · Updated Jul 27, 2026
Reachable assertion in ggml.ai whisper.cpp 95ea8f9b allows local users to crash model-loading processes via a malformed model file. The whisper_model_load() path passes a model-declared ftype to ggml_ftype_to_ggml_type(), which converts invalid values to GGML_TYPE_COUNT and immediately asserts instead of returning a load error. Local low-privileged access is required; loading the crafted model aborts the invoking process, without reported data disclosure or modification.
Summary
What happened
Reachable assertion in ggml.ai whisper.cpp 95ea8f9b allows local users to crash model-loading processes via a malformed model file. The whisper_model_load() path passes a model-declared ftype to ggml_ftype_to_ggml_type(), which converts invalid values to GGML_TYPE_COUNT and immediately asserts instead of returning a load error. Local low-privileged access is required; loading the crafted model aborts the invoking process, without reported data disclosure or modification.
The record
- CVE
- CVE-2026-17513
- Published
- Jul 27, 2026
- Updated
- Jul 27, 2026
- Vendor
- Georgi Gerganov
- Product
- whisper.cpp
- Classifications
- CWE-617, T1499.004
- Attack vector
- local
- Privileges
- authenticated
Timeline
How it unfolded
- Jul 27, 2026CVE publishedPublication date reported by the CVE source.
- Jul 27, 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=95ea8f9b
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.
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