{
 "id": "https://redfinchadvisory.com/lexicon/data-exfiltration",
 "slug": "data-exfiltration",
 "prefLabel": "Data exfiltration",
 "altLabel": [
  "Data leakage",
  "Data leak"
 ],
 "hiddenLabel": [],
 "definition": "A type of AI system attack which attempts to have the system send private data outside your company or to anyone not permitted to see it.",
 "scopeNote": "Permissions are the strongest defense: an agent that can't access sensitive data, or can't send anything out, can't leak it. Guardrails reduce the risk but can't make this attack impossible.",
 "tier": null,
 "group": "Risks",
 "broader": [
  "https://redfinchadvisory.com/lexicon/ai-security"
 ],
 "narrower": [],
 "related": [
  {
   "id": "https://redfinchadvisory.com/lexicon/output-guardrail",
   "type": "related"
  },
  {
   "id": "https://redfinchadvisory.com/lexicon/pii-redaction",
   "type": "related"
  },
  {
   "id": "https://redfinchadvisory.com/lexicon/indirect-prompt-injection",
   "type": "related"
  }
 ],
 "links": [
  {
   "id": "https://redfinchadvisory.com/lexicon/least-privilege-for-ai",
   "label": "is best stopped by",
   "direction": "out"
  }
 ],
 "modified": "2026-10-21",
 "markdown": "https://redfinchadvisory.com/lexicon/data-exfiltration.md",
 "inScheme": {
  "id": "https://redfinchadvisory.com/lexicon",
  "version": "1.0",
  "currentAsOf": "2026-10-21"
 }
}