# CVE-2026-86317: ggml-org llama.cpp RPC Server ggml-rpc.cpp deserialize_tensor assertion

> Remote attackers can crash the llama.cpp RPC server by sending manipulated tensor data, causing a denial of service.

- **Severity:** Medium 6.9 (`CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:X`)
- **Exploited in the wild:** Not known
- **Login needed:** Not needed
- **Attackable:** Over the internet
- **Victim action needed:** Not needed
- **Fix available:** No
- **Published:** 7 Sep 2026
- **Updated:** 8 Sep 2026
- **Also known as:** DEBIAN-CVE-2026-86317, GHSA-c676-w283-jfxr, UBUNTU-CVE-2026-86317

## What is CVE-2026-86317?

CVE-2026-86317 is a medium-severity denial of service vulnerability in ggml-org llama.cpp, published on 7 Sep 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.

### Official description

A vulnerability was detected in ggml-org llama.cpp up to 0.4.0. This impacts the function rpc_server::deserialize_tensor of the file ggml/src/ggml-rpc/ggml-rpc.cpp of the component RPC Server. Performing a manipulation of the argument ne results in reachable assertion. The attack is possible to be carried out remotely. The reported GitHub issue was closed automatically due to inactivity.

Weakness: CWE-617 (Reachable Assertion)

## Which versions are affected by CVE-2026-86317?


## How do I fix CVE-2026-86317?

No fix has been published for CVE-2026-86317 yet. Limit exposure of the affected software until one is available.

## Is CVE-2026-86317 being exploited?

There is no known exploitation of CVE-2026-86317 in the wild and no public exploit code.

## Fix prompt for AI coding agents

```text
Check this codebase for CVE-2026-86317 and fix it if it is affected.

What it is: CVE-2026-86317 is a medium-severity denial of service vulnerability in ggml-org llama.cpp, published on 7 Sep 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Exploitation: There is no known exploitation of CVE-2026-86317 in the wild and no public exploit code.

Affected product: ggml-org llama.cpp. No package-level version data is available, so check the vendor advisory linked from the reference page.

Task:
1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.
2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.
3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.
4. Run the tests and summarise what changed and why.
5. If nothing in the project is affected, say so and change nothing.

Reference: https://insights.sbomify.com/CVE-2026-86317/ (Markdown: https://insights.sbomify.com/CVE-2026-86317/index.md)
```

## Sources

- CVE record: https://www.cve.org/CVERecord?id=CVE-2026-86317
- NVD: https://nvd.nist.gov/vuln/detail/CVE-2026-86317
- OSV: https://osv.dev/vulnerability/CVE-2026-86317

---
From sbomify Insights: https://insights.sbomify.com/CVE-2026-86317/
Summaries are generated and may contain mistakes; the official description above is the record.