AI-Enabled Exfiltration
Technique · ATTACK:enterprise:T1700
Attributed source ↗ · Plaintext record · Complete record and assertions JSON
Inspect structured metadata and provenance
{
"id": "ATTACK:enterprise:T1700",
"title": "AI-Enabled Exfiltration",
"type": "Technique",
"source_url": "https://attack.mitre.org/techniques/T1700",
"snapshot": "enterprise-attack-20.0.json",
"status": "active",
"rights": "Source metadata only; source notices retained; no operational prose or payloads",
"review_status": "machine-extracted; source-specific checks passed, editorial review pending",
"stix_id": "attack-pattern--c0a6e9ec-9ef1-46b6-8a71-cc73863e8985",
"external_id": "T1700",
"domain": "enterprise",
"created": "2026-09-22T01:25:32.738Z",
"modified": "2026-10-09T16:32:40.851Z",
"version": "1.0",
"aliases": [
],
"tactics": [
"exfiltration"
],
"source_references": [
{
"source_name": "Anthropic Report Sep 2026",
"url": "https://www.anthropic.com/threat-intelligence-report-september-2026"
},
{
"source_name": "Google Cloud AI Risk Sep 2026",
"url": "https://cloud.google.com/security/resources/ai-risk-and-resilience-2026"
},
{
"source_name": "Barracuda Prompt Injection Phishing Emails",
"url": "https://blog.barracuda.com/2026/10/07/email-attacks-target-both-humans-ai-assistants"
},
{
"source_name": "Prompt-Injection Exfil",
"url": "https://arxiv.org/html/2608.27092"
},
{
"source_name": "Google Security State of Prompt Injections",
"url": "https://blog.google/security/prompt-injections-web/"
}
]
}Explicit source assertions (3)
First 80 shown here; the complete set is in this record’s JSON and plaintext. Each relationship retains its source and locator. No inferred relationships are added.
ATTACK:enterprise:M1017 → mitigates → ATTACK:enterprise:T1700
MITRE ATT&CK: Source assertion; no new actor identity, alias equivalence, CVE exploitation or causal inference. Procedure prose omitted.
Assertion source · Locator: relationship--635477d8-e634-4f6b-acdf-2cccb27061fa
ATTACK:enterprise:M1048 → mitigates → ATTACK:enterprise:T1700
MITRE ATT&CK: Source assertion; no new actor identity, alias equivalence, CVE exploitation or causal inference. Procedure prose omitted.
Assertion source · Locator: relationship--93499a37-35b3-4b66-8275-b53542c4341f
ATTACK:enterprise:M1022 → mitigates → ATTACK:enterprise:T1700
MITRE ATT&CK: Source assertion; no new actor identity, alias equivalence, CVE exploitation or causal inference. Procedure prose omitted.
Assertion source · Locator: relationship--f41d077c-c8f4-485b-b557-54231e82be7f