{
 "id": "https://redfinchadvisory.com/lexicon/prompt-injection",
 "slug": "prompt-injection",
 "prefLabel": "Prompt injection",
 "altLabel": [],
 "hiddenLabel": [],
 "definition": "A type of AI system attack where text the system reads contains instructions, and the system follows them as if they came from its user or owner.",
 "scopeNote": "Prompt injection is one of the most basic and most effective attacks that systems need to defend against, and there is no complete fix today. Limiting what the system can access and do reduces the damage.",
 "tier": null,
 "group": "Risks",
 "broader": [
  "https://redfinchadvisory.com/lexicon/ai-security"
 ],
 "narrower": [],
 "related": [
  {
   "id": "https://redfinchadvisory.com/lexicon/jailbreak",
   "type": "confused"
  },
  {
   "id": "https://redfinchadvisory.com/lexicon/input-guardrail",
   "type": "related"
  }
 ],
 "links": [
  {
   "id": "https://redfinchadvisory.com/lexicon/indirect-prompt-injection",
   "label": "includes",
   "direction": "out"
  }
 ],
 "modified": "2026-10-21",
 "markdown": "https://redfinchadvisory.com/lexicon/prompt-injection.md",
 "inScheme": {
  "id": "https://redfinchadvisory.com/lexicon",
  "version": "1.0",
  "currentAsOf": "2026-10-21"
 }
}