- CVSS
- HIGH · 7.5v3.1CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- Published
- 2026-10-29
- Weakness
- CWE-248
- Source
- nvd.nist.gov/vuln/detail/CVE-2026-119052
Description
llama.cpp b2877 before b11935 contains an uncaught exception vulnerability in the ggml-rpc server that allows unauthenticated remote attackers to crash the rpc-server by sending oversized message lengths. After the HELLO handshake, attackers can send a command such as SET_TENSOR with a length above std::vector::max_size(), triggering an uncaught std::length_error that aborts the process and denies service to all clients.
References
- https://github.com/ggml-org/llama.cpp
- https://github.com/ggml-org/llama.cpp/blob/8542e94350f0ade01644db6f1d1520da3814dafd/ggml/src/ggml-rpc/ggml-rpc.cpp#L344-L356
- https://github.com/ggml-org/llama.cpp/commit/7ecb57f7adbea2928aa468ad2aecf05b10725ad4
- https://github.com/ggml-org/llama.cpp/pull/31204
- https://github.com/ggml-org/llama.cpp/releases/tag/b11935
- https://www.vulncheck.com/advisories/llama-cpp-b2877-before-b11935-ggml-rpc-server-dos-via-oversized-recv-msg-length
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-119052 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.