# Prompt Injection Source: https://customlabs.io/glossary/prompt-injection/ Updated: 2026-09-13 Evaluation # Prompt Injection Prompt injection is untrusted input crafted to override a model's system prompt or task. It matters most once a model can retrieve untrusted content or call tools. A successful injection can turn a summarization task into an unauthorized action. Defending against it takes input and output evals and guardrails, not a stricter system prompt. The system prompt cannot defend itself, because it is exactly what is being attacked. [Insight: Evals before you ship](https://customlabs.io/insights/evals-before-you-ship/)[Field guide: Failure modes](https://customlabs.io/failure-modes/) [← Back to the full glossary](https://customlabs.io/glossary/) ## Related terms [Guardrails Guardrails are the checks that keep an LLM or agent inside acceptable bounds in production.](https://customlabs.io/glossary/guardrails/)[Tool Poisoning Tool poisoning hides an instruction in a tool's description that the model reads as legitimate.](https://customlabs.io/glossary/tool-poisoning/)[Hallucination A hallucination is a confident, fluent output that is factually wrong or unsupported.](https://customlabs.io/glossary/hallucination/)[Red Teaming Red teaming is deliberately attacking your own AI system to find what breaks first.](https://customlabs.io/glossary/red-teaming/) ## More in Evaluation [Eval Suite (Evals) An eval suite is a versioned set of test cases that measures whether outputs are good.](https://customlabs.io/glossary/eval-suite/)[LLM-as-Judge LLM-as-judge uses another LLM to score a model's outputs against a rubric, at scale.](https://customlabs.io/glossary/llm-as-judge/)[Observability Observability captures traces of every prompt, retrieval, tool call, and response for debugging.](https://customlabs.io/glossary/observability/)[Shadow Deployment A shadow deployment runs a candidate release against real production traffic, offline, before release.](https://customlabs.io/glossary/shadow-deployment/)