AI Glossary

Prompt injection

An attack in which input makes a model behave in ways its builders did not intend, either typed directly or hidden in content the model reads, such as a web page, an email or a document. OWASP's 2025 list ranks it first among the security risks for applications built on language models.

See also

  • Jailbreak

    A prompt crafted to get a model to ignore its safety training and produce something it was trained to refuse.

  • Guardrail

    A rule or check around a model that blocks or corrects unwanted input or output, such as a filter for unsafe content or a limit on which actions an agent may take.

  • Sandbox

    An isolated environment in which an agent can run code or use tools with limited access to files, networks and other systems, as far as its configuration allows.

  • Red teaming

    Deliberately attacking an AI system the way an adversary would, to find harmful outputs, security holes or failures, before or after it is released.

Source: OWASP, LLM01:2025 Prompt Injection (opens in a new tab)

Cite this term.

CC BY 4.0, attribution required.

This term

Orbyt Labs, Prompt injection (AI Glossary), Oct 18, 2026. https://www.orbytlabs.ai/orbyt-collective/glossary/prompt-injection

The dataset (JSON)

Orbyt Labs Glossaries (Oct 19, 2026), https://www.orbytlabs.ai/glossary#dataset

Last updated .