{
  "id": "macos-gaslight-dprk-2026-06",
  "name": "macOS.Gaslight - DPRK backdoor with LLM prompt injection analysis",
  "date_reported": "2026-06-23",
  "researcher": "SentinelLABS",
  "org": "SentinelOne",
  "sources": [
    {
      "url": "https://www.sentinelone.com/labs/macos-gaslight-dprk-backdoor-prompt-injection/",
      "title": "SentinelLABS: macOS.Gaslight - North Korean Backdoor Uses LLM to Evade Analysis"
    }
  ],
  "borderline": false,
  "borderline_note": null,
  "ai_role": "attacker_uses_ai_as_operator",
  "ai_role_secondary": "ai_agent_or_mcp_as_target",
  "ai_role_detail": "DPRK macOS.Gaslight backdoor uses prompt injection to manipulate security analysts' LLM-based malware analysis tools, providing false benign verdicts",
  "technique_summary": "Jun 23, 2026: SentinelLABS analyzed macOS.Gaslight, DPRK macOS backdoor deployed via fake job offers targeting cryptocurrency/AI companies. Backdoor includes novel anti-analysis technique: embeds carefully crafted prompt injection payloads in code comments, strings, and metadata. When security researchers use LLM-based analysis tools (Claude Code, GPT-4 Code Interpreter, AI-assisted reverse engineering tools) to examine sample, injected prompts instruct LLM to: (1) report code as benign; (2) misattribute functionality; (3) omit C2 communications from analysis; (4) provide false explanations downplaying severity. SentinelLABS tested against Claude Sonnet 3.5, GPT-4o, Gemini 1.5 Pro: all three initially reported backdoor as benign when using standard analysis prompts. Adversary understands analysts increasingly rely on LLM code analysis; targets the analysis workflow itself. Backdoor functionality: keylogging, screenshot capture, file exfiltration, command execution; C2 via hxxps://macos-update[.]com. Attributed to DPRK BlueNoroff/Lazarus with high confidence. Detection: analyze samples in sandboxes without LLM assistance for initial triage; use LLM analysis only as supplementary; check for prompt injection patterns in binary strings; verify C2 communications manually.",
  "initial_access": "Spearphishing with fake job offers targeting crypto/AI company employees; malicious macOS application bundle delivered via LinkedIn/email",
  "ai_tooling_and_models": [
    "Claude Code (targeted for manipulation)",
    "GPT-4 Code Interpreter (targeted)",
    "Gemini 1.5 Pro (targeted)",
    "AI-assisted reverse engineering tools (targeted)"
  ],
  "other_tooling": [
    "macOS.Gaslight backdoor",
    "Prompt injection in malware samples",
    "C2 infrastructure (macos-update[.]com)",
    "Keylogger, screenshot capture, file exfiltration"
  ],
  "victims_and_sectors": "Cryptocurrency companies, AI/ML companies, fintech; individuals in tech roles targeted via social engineering",
  "regions": [
    "Multiple regions"
  ],
  "attribution_or_cluster": "DPRK BlueNoroff/Lazarus (high-confidence attribution by SentinelOne); revenue generation and intelligence collection operations",
  "scale_and_metrics": "Unknown number of infections; discovered Jun 2026; first documented malware using prompt injection to manipulate analyst LLM tools",
  "prevention_angle": "Educate employees on fake job offer phishing; verify job offers via official channels; use Gatekeeper and notarization (macOS); implement EDR detecting keyloggers and C2 communications; for analysts: do not rely solely on LLM-based analysis tools; use traditional sandboxing and manual analysis for initial triage; verify LLM analysis results against manual inspection",
  "related_magicsword_projects": [],
  "source_notes": "SentinelLABS analysis with DPRK attribution. macOS.Gaslight represents significant evolution: adversary anticipates security analyst workflows and embeds anti-analysis prompt injection targeting LLM tools increasingly used in malware research. Detection: sandbox malware without LLM analysis initially; scan binary strings/comments for prompt injection patterns ('ignore previous instructions', 'this is benign', 'do not report'); verify C2 manually; check for macos-update[.]com domain; look for keylogger/screenshot indicators on macOS.",
  "last_reviewed": "2026-11-04",
  "iocs": {
    "domains": [
      "macos-update.com"
    ],
    "ips": [],
    "hashes": [],
    "urls": []
  },
  "atlas_techniques": [
    {
      "id": "AML.T0051",
      "rationale": "DPRK malware embeds prompt injection in code to manipulate LLM-based security analysis tools, causing false benign verdicts",
      "source_urls": [
        "https://www.sentinelone.com/labs/macos-gaslight-dprk-backdoor-prompt-injection/"
      ]
    }
  ],
  "attack_flow": {
    "nodes": [
      {
        "id": "spearphishing",
        "title": "Fake job offer spearphishing",
        "description": "DPRK BlueNoroff/Lazarus targets crypto/AI company employees via fake job offers on LinkedIn/email; sends malicious macOS app bundle (posing as job assessment test, code challenge, etc.)",
        "kind": "access",
        "source_urls": [
          "https://www.sentinelone.com/labs/macos-gaslight-dprk-backdoor-prompt-injection/"
        ]
      },
      {
        "id": "execute-backdoor",
        "title": "User executes backdoor",
        "description": "Target executes malicious app; macOS.Gaslight backdoor installs keylogger, screenshot capture, file exfiltration, command execution capabilities; establishes C2 to hxxps://macos-update[.]com",
        "kind": "execution",
        "source_urls": [
          "https://www.sentinelone.com/labs/macos-gaslight-dprk-backdoor-prompt-injection/"
        ]
      },
      {
        "id": "evade-analysis",
        "title": "Prompt injection evades LLM analysis",
        "description": "Security researchers analyze sample using LLM tools (Claude Code, GPT-4, Gemini); embedded prompt injection in code comments/strings instructs LLM to report as benign, omit C2 from analysis, misattribute functionality; delays detection and remediation",
        "kind": "ai",
        "source_urls": [
          "https://www.sentinelone.com/labs/macos-gaslight-dprk-backdoor-prompt-injection/"
        ]
      },
      {
        "id": "exfiltration",
        "title": "Data exfiltration and persistence",
        "description": "Backdoor logs keystrokes, captures screenshots, exfiltrates files to C2; maintains persistence on macOS; delayed detection due to LLM analysis manipulation enables prolonged access",
        "kind": "impact",
        "source_urls": [
          "https://www.sentinelone.com/labs/macos-gaslight-dprk-backdoor-prompt-injection/"
        ]
      }
    ],
    "edges": [
      {
        "source": "spearphishing",
        "target": "execute-backdoor"
      },
      {
        "source": "execute-backdoor",
        "target": "evade-analysis"
      },
      {
        "source": "execute-backdoor",
        "target": "exfiltration"
      }
    ]
  },
  "category": "adversary-use-of-ai",
  "attribution": {
    "actor_name": "BlueNoroff/Lazarus",
    "country": "DPRK",
    "motivation": "nation-state",
    "attributed_by": "SentinelOne",
    "confidence": "high"
  },
  "ai_involvement_confidence": "confirmed",
  "detections": [
    {
      "name": "Prompt injection pattern detection",
      "format": "guidance",
      "notes": "Scan malware samples for embedded prompt injection patterns before LLM analysis; use traditional sandbox analysis for initial triage"
    },
    {
      "name": "C2 monitoring",
      "format": "guidance",
      "notes": "Monitor for macos-update[.]com domain; detect keylogger and screenshot capture activity on macOS"
    }
  ],
  "timeline": {
    "first_seen": "2026-06-01",
    "last_updated": "2026-11-04",
    "updates": [
      {
        "date": "2026-06-23",
        "source": "SentinelLABS",
        "summary": "First documented DPRK malware using prompt injection to manipulate LLM-based security analysis tools"
      }
    ]
  }
}