Vulnerability Description
llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the n_discard parameter is parsed directly from JSON input in the llama.cpp server's completion endpoints without validation to ensure it's non-negative. When a negative value is supplied and the context fills up, llama_memory_seq_rm/add receives a reversed range and negative offset, causing out-of-bounds memory writes in the token evaluation loop. This deterministic memory corruption can crash the process or enable remote code execution (RCE). There is no fix at the time of publication.
CVSS Score
HIGH
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Ggml | Llama.Cpp | - |
Related Weaknesses (CWE)
References
- https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3cExploitVendor Advisory
- https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3cExploitVendor Advisory
FAQ
What is CVE-2026-21869?
CVE-2026-21869 is a vulnerability with a CVSS score of 8.8 (HIGH). llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the n_discard parameter is parsed directly from JSON input in the llama.cpp server's completion endpoints with...
How severe is CVE-2026-21869?
CVE-2026-21869 has been rated HIGH with a CVSS base score of 8.8/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-21869?
Check the references section above for vendor advisories and patch information. Affected products include: Ggml Llama.Cpp.