Concept dictionary
Prompt Injection
Prompt injection is an attack in which instructions placed in user input or retrieved content attempt to override, redirect, or exploit an AI system's intended instructions and tool access.
- Review state
- Reviewed in POC
- Freshness
- Current
- Version
- 2
Also called
- Prompt Injection
- Indirect Prompt Injection
Remember it this wayUntrusted content tries to become trusted instruction.
In plain language
A model may encounter text that looks like a new command inside a document, webpage, email, or direct request. If the surrounding system treats that content as trusted instruction, the model may follow it.
Why it matters
Systems that read untrusted content or use tools can expose data or take unwanted actions unless permissions and trust boundaries are enforced outside the prompt.
Example
A document contains hidden text telling an assistant to ignore its task and send retrieved confidential information to an external address.
Common misconception
Prompt injection cannot be solved reliably by adding one stronger sentence to the system prompt. It requires architectural controls, limited permissions, isolation, and monitoring.
Related terms
Sources
- NIST AI 100-2 E2025, Adversarial Machine Learningauthoritative taxonomy and definition of prompt-injection attacks.
Learn more
- Treat retrieved content as untrusted input and preserve boundaries around [[sensitive-information|Sensitive Information]].