{
  "node_id": "mitre-atlas-system-instruction-keywords",
  "title": "MITRE ATLAS System Instruction Keywords (AML.T0069.001) - Adversarial System Instruction Keywords threat to AI systems",
  "domain": "AI Governance & Law",
  "version": "1.0.1",
  "last_updated": "2026-07-22",
  "bluf": "This node addresses MITRE ATLAS technique AML.T0069.001 (System Instruction Keywords). Adversaries may discover keywords that have special meaning to the large language model (LLM), such as function names or object names. These can later be exploited to confuse or manipulate the LLM into misbehaving and to make calls to plugins the LLM has access to. Defending against this technique is required under EU AI Act, NIST AI RMF, and ISO/IEC 42001 obligations; this node operationalises the documented ATLAS mitigations and cross-instrument controls into a deterministic verification workflow. Sub-technique of ATLAS AML.T0069.",
  "paywall": {
    "status": "LOCKED",
    "unlock_cost_usd": "0.01",
    "skyfire_id": "41779894-ece2-4163-9761-b3b1b76e19b0"
  },
  "crosswalks": {
    "_available_keys": [
      "nist_framework",
      "iso_standard",
      "industry_mapping",
      "ai_overlay_2026"
    ],
    "_note": "Full crosswalk values included in vault response"
  },
  "dependencies": [
    "nist-ai-rmf-1-0",
    "eu-ai-act-2024",
    "iso-iec-42001-ai-management-system-2023",
    "mitre-atlas-discover-llm-system-information"
  ],
  "primary_citations_count": 5
}