Glossary
Prompt Injection
An attack where malicious instructions hidden in input get a model to ignore its rules - the AI equivalent of an injection vulnerability.
Prompt injection slips adversarial instructions into content a model processes - a user message, a web page, a document, or a tool result - to override its system prompt or trigger unintended actions.
Indirect prompt injection, where the payload arrives through retrieved data rather than the user, is especially dangerous for agents that can act. Runtime guardrails and least-privilege tool access reduce the blast radius.
Govern AI like infrastructure.
Talk to our team about deploying DataStrict across your enterprise stack.