Checked fact 98410 Oct 2026Safety and security

OWASP says indirect prompt injections occur "when an LLM accepts input from external sources, such as websites or files" and that the content, when interpreted by the model, alters its behavior in unintended or unexpected ways.

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

Indirect prompt injections occur when an LLM accepts input from external sources, such as websites or files. The content may have in the external content data that when interpreted by the model, alters the behavior of the model in unintended or unexpected ways.

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

The source

LLM01:2025 Prompt Injection
OWASP Gen AI Security Project

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

“OWASP says indirect prompt injections occur "when an LLM accepts input from external sources, such as websites or files" and that the content, when interpreted by the model, alters its behavior in unintended or unexpected ways.” ai notis, checked 10 Oct 2026. Source: LLM01:2025 Prompt Injection (OWASP Gen AI Security Project). https://ainotis.com/c/984

As a reference (APA style)

ai notis. (2026, October 10). OWASP says indirect prompt injections occur "when an LLM accepts input from external sources, such as websites or files" and that the content, when interpreted by the model, alters its behavior in unintended or unexpected ways [Checked claim 984]. ai notis. https://ainotis.com/c/984

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