Description
A vulnerability was found in ggml-org llama.cpp bec4772f6. The impacted element is the function deserialize_tensor of the file ggml/src/ggml-rpc/ggml-rpc.cpp of the component ggml-RPC Server. Performing a manipulation of the argument op/op_params results in deserialization. The attack may be initiated remotely. This vulnerability is distinct from CVE-2026-34159 (GHSA-j8rj-fmpv-wcxw, PR #20908), which only added a buffer==nullptr rejection in create_node() and does not validate op or op_params. The reported GitHub issue was closed automatically due to inactivity.
Affected products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| ggml-org | llama.cpp | bec4772f6 | — |
Fixed in Linux distributions
Distributions backport fixes, so the version that fixes this vulnerability differs per release — upgrade to at least the version shown. From the distributions' security trackers and advisories.
Debian
Security tracker ↗| Release | Package | Fixed in | Advisory |
|---|---|---|---|
| Debian 14 | llama.cpp | No fix yet | — |
Ubuntu
Security tracker ↗| Release | Package | Fixed in | Advisory |
|---|---|---|---|
| Ubuntu 26.10 | llama.cpp | No fix yet | — |
| Ubuntu 26.04 LTS | llama.cpp | No fix yet | — |
References
- VDB-394534 | ggml-org llama.cpp ggml-RPC Server ggml-rpc.cpp deserialize_tensor deserialization vdb-entry technical-description
- VDB-394534 | CTI Indicators (IOB, IOC, IOA) signature permissions-required
- CVE-2026-78147 | CVE Analysis and Report third-party-advisory
- Submit #882534 | ggml-org llama.cpp master bec4772f6 Memory Corruption third-party-advisory
- https://github.com/ggml-org/llama.cpp/issues/25289 issue-tracking
- https://github.com/ggml-org/llama.cpp/ product