Direct Prompt Injection

Technique · ATTACK:enterprise:T1699

Attributed source ↗ · Plaintext record · Complete record and assertions JSON

Inspect structured metadata and provenance

{
  "id": "ATTACK:enterprise:T1699",
  "title": "Direct Prompt Injection",
  "type": "Technique",
  "source_url": "https://attack.mitre.org/techniques/T1699",
  "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--d7e9cba9-3b43-4208-8e90-fdb18bff4a6a",
  "external_id": "T1699",
  "domain": "enterprise",
  "created": "2026-09-18T17:58:36.690Z",
  "modified": "2026-09-22T13:44:19.807Z",
  "version": "1.0",
  "aliases": [

  ],
  "tactics": [
    "execution"
  ],
  "source_references": [
    {
      "source_name": "Gemini AI Misuse Jan 2025",
      "url": "https://services.google.com/fh/files/misc/adversarial-misuse-generative-ai.pdf"
    },
    {
      "source_name": "NIST Direct Prompt Injection",
      "url": "https://csrc.nist.gov/glossary/term/direct_prompt_injection"
    },
    {
      "source_name": "OWASP Prompt Injection",
      "url": "https://genai.owasp.org/llmrisk/llm01-prompt-injection/"
    },
    {
      "source_name": "Palo Alto Prompt Injection",
      "url": "https://www.paloaltonetworks.com/cyberpedia/what-is-a-prompt-injection-attack"
    },
    {
      "source_name": "Cybersec Guru Prompt Injection",
      "url": "https://thecybersecguru.com/news/instagram-meta-ai-vulnerability-account-recovery-exploit/"
    }
  ]
}

Explicit source assertions (6)

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.