Vulnerability 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.
CVSS Score
HIGH
Related Weaknesses (CWE)
References
- https://github.com/ggml-org/llama.cpp
- https://github.com/ggml-org/llama.cpp/blob/8542e94350f0ade01644db6f1d1520da3814d
- https://github.com/ggml-org/llama.cpp/commit/7ecb57f7adbea2928aa468ad2aecf05b107
- 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-serv
FAQ
What is CVE-2026-119052?
CVE-2026-119052 is a vulnerability with a CVSS score of 7.5 (HIGH). 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 leng...
How severe is CVE-2026-119052?
CVE-2026-119052 has been rated HIGH with a CVSS base score of 7.5/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-119052?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.