CVE-2026-21869
What it is
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.
At a glance
- Exploitability
- Can be exploited over the network without logging in, but needs a user to act. High risk of data exposure, data tampering, service disruption.
- Exploit odds
- 0.5% chance of exploitation in the next 30 days (EPSS).
- Fix
- A patch, advisory or fixed version is referenced. Upgrade or apply it.
Timeline
- PublishedDisclosed publicly on CVE.org and NVD
- Last updatedMost recent change to the record
Why it ranks here
- Exploited in the wild: no, CISA does not list it.
- Exploit odds: 0.5% in the next 30 days (EPSS).
- Severity: 8.8 HIGH (CVSS).
- Fix: a patch or advisory is linked.
Details
- Published
- Last modified
- Exploit probability
- 0.5% · EPSS, next 30 days
- Weakness
- CWE-787 · Out-of-bounds write
- Record status
- Analyzed
Affected
- Ggml llama.cpp
Attack profile CVSS 3.1 · 8.8
- Attack vector
- Network
- Complexity
- Low
- Privileges needed
- None
- User interaction
- Required
- Scope
- Unchanged
- Confidentiality
- High
- Integrity
- High
- Availability
- High
Raw vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Is it in your code?
Hand this to your coding agent. It searches your project for the affected products and checks versions. Nothing leaves your machine.
Read https://cve-list.com/agent/cve/CVE-2026-21869.md and follow it. Check whether this project is affected by CVE-2026-21869. Read only. Don't change anything and don't upload my code. Tell me yes, no or not sure, with the file as proof.
Fix and advisories
- https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c
- https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c