Skip to content

Glossary · Security

Indirect prompt injection

Indirect prompt injection is prompt injection delivered through content an AI system reads, such as a web page, email, document or tool result, rather than typed by the user.

Reviewed 15 November 2026

Greshake et al. showed attackers can plant instructions in data that LLM-integrated apps retrieve, leading to data theft, misinformation or unwanted actions without the user noticing.

Agents are especially exposed because they read untrusted content and can act on it. Treat every retrieved or tool-returned text as data, never as instructions, and limit what an agent can do without confirmation.

Learn more on Kojen

Sources

  1. [1]Greshake et al., 2023. Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection (arXiv:2302.12173)
  2. [2]OWASP. OWASP Top 10 for Agentic Applications for 2026

All 31 terms

Put the definitions to work.

Kojen evaluates, tunes and red-teams your agents with these methods built in: Wilson intervals, pass^k, LLM judges with visible components. Free to start.

Start training free