Unauthenticated code execution via deserialized function pointer
Published Aug 23, 2026 · Updated Aug 23, 2026
Deserialization in the ggml-RPC Server in ggml.ai llama.cpp bec4772f6 allows remote attackers to execute code via crafted tensor fields. deserialize_tensor copies network-controlled op and op_params values without validation; custom-operation execution then treats op_params as a function pointer and argument. The RPC backend must be enabled and reachable, but it provides no authentication, and successful exploitation transfers control to an attacker-selected address.
Summary
What happened
Deserialization in the ggml-RPC Server in ggml.ai llama.cpp bec4772f6 allows remote attackers to execute code via crafted tensor fields. deserialize_tensor copies network-controlled op and op_params values without validation; custom-operation execution then treats op_params as a function pointer and argument. The RPC backend must be enabled and reachable, but it provides no authentication, and successful exploitation transfers control to an attacker-selected address.
The record
- CVE
- CVE-2026-78147
- Published
- Aug 23, 2026
- Updated
- Aug 23, 2026
- Vendor
- Georgi Gerganov
- Product
- llama.cpp
- Classifications
- CWE-502, CWE-20, T1190
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Aug 23, 2026CVE publishedPublication date reported by the CVE source.
- Aug 23, 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=bec4772f6
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