Checked fact 34162 Nov 2026Agents and apps

DeepSeek's SAFETY.md calls the software experimental developer-preview software that has not had a security audit, and says it can run model-generated code and commands and reach the network, processes, credentials and files.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

DeepSeek Harness is experimental developer-preview software. It has not undergone a security audit and must not be treated as secure or production-ready. The project can execute model-generated code and commands, load third-party plugins, and access the network, processes, credentials, and files made available to it.

What the source said when we opened it, on 2 Nov 2026.

The source

DeepSeek Harness safety notice (SAFETY.md)
DeepSeek AI (GitHub)

Open the source archived copy

Checked

Checked by the notis newsroom on 2 Nov 2026, against the source above.

In the story

DeepSeek's open-source Harness agent framework warns it has had no security audit 2 Nov 2026

Cite this fact

Short permanent address

In a sentence

“DeepSeek's SAFETY.md calls the software experimental developer-preview software that has not had a security audit, and says it can run model-generated code and commands and reach the network, processes, credentials and files.” ai notis, checked 2 Nov 2026. Source: DeepSeek Harness safety notice (SAFETY.md) (DeepSeek AI (GitHub)). https://ainotis.com/c/3416

As a reference (APA style)

ai notis. (2026, November 2). DeepSeek's SAFETY.md calls the software experimental developer-preview software that has not had a security audit, and says it can run model-generated code and commands and reach the network, processes, credentials and files [Checked claim 3416]. ai notis. https://ainotis.com/c/3416

Anyone may quote this address. It does not change; if we correct the story, this page says so.