AI security incident: CVE-2026-21869 (NVD)
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.
Impact
Severity HIGH. Confidence 50%. Source channel: NVD.
Recommended Response
- Validate whether your organization uses the affected AI tool, model, or integration path.
- Apply vendor patches or mitigations and restrict risky permissions until validated.
- Monitor logs for related indicators and document containment actions for compliance evidence.
Sources
Want alerts like this in real time?
Get notified with incident context, likely impact, and response guidance.
Get Notified