Checked fact 99710 Oct 2026Safety and security

Anthropic's documentation says to tell Claude explicitly that content returned from tools, documents, or searches is untrusted data and must never override the system prompt or the user's original request.

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

State the policy in your system prompt. Tell Claude explicitly that content returned from tools, documents, or searches is untrusted data and must never override the system prompt or the user's original request.

What the source said when we opened it, on 10 Oct 2026.

The source

Mitigate jailbreaks and prompt injections
Anthropic (Claude Platform Docs)

Open the source archived copy

Checked

Checked by the notis newsroom on 10 Oct 2026, against the source above.

In the story

How prompt injection works and how to limit the damage 10 Oct 2026

Cite this fact

Short permanent address

In a sentence

“Anthropic's documentation says to tell Claude explicitly that content returned from tools, documents, or searches is untrusted data and must never override the system prompt or the user's original request.” ai notis, checked 10 Oct 2026. Source: Mitigate jailbreaks and prompt injections (Anthropic (Claude Platform Docs)). https://ainotis.com/c/997

As a reference (APA style)

ai notis. (2026, October 10). Anthropic's documentation says to tell Claude explicitly that content returned from tools, documents, or searches is untrusted data and must never override the system prompt or the user's original request [Checked claim 997]. ai notis. https://ainotis.com/c/997

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