{
  "id": "symantec-aoki-infostealer-ai-2026-10",
  "name": "Aoki infostealer targets Claude Code, ChatGPT, Codex, Cursor tokens",
  "date_reported": "2026-10-15",
  "researcher": "Symantec Threat Hunter Team, Check Point Research",
  "org": "Broadcom (Symantec), Check Point",
  "sources": [
    {
      "url": "https://www.broadcom.com/support/security-center/protection-bulletin/aoki-infostealer-targets-ai-coding-assistant-credentials",
      "title": "Aoki: Infostealer Targets AI Coding Assistant Credentials"
    },
    {
      "url": "https://www.security.com/threat-intelligence/aoki-infostealer-ai-targeting",
      "title": "Symantec Aoki AI targeting"
    },
    {
      "url": "https://research.checkpoint.com/2026/infostealer-riding-the-ai-train/",
      "title": "Check Point: Infostealer riding the AI Train"
    }
  ],
  "borderline": false,
  "borderline_note": null,
  "ai_role": "ai_credential_theft",
  "ai_role_secondary": null,
  "ai_role_detail": "Recent Aoki/Aokigahara infostealer builds steal AI coding assistant credentials, session files, and tokens",
  "technique_summary": "Aoki (aka Aokigahara) infostealer added AI credential theft in 2026. Targets: .claude.json, Claude desktop cookies, ChatGPT cookies, Codex config.toml/.env (github.com/openai/codex-cli), GitHub Copilot tokens (github.com/features/copilot), Cursor state.vscdb/storage.json (github.com/getcursor/cursor), Gemini CLI, JetBrains AI Assistant, Kiro, Windsurf, Codeium (github.com/Exafunction/codeium.vim), AWS credentials/SSO, Amazon Q, Git credentials, SSH keys. Cursor local state caches chat/code. Stolen keys allow acting under developer identity/quota, expose repos/cloud/CI-CD, bypass safeguards. Capable of LLMjacking. Earlier 2026 versions didn't target AI; capability recently added/expanding. Detection: monitor AI credential file access (.claude.json, .codex/auth.json, Cursor globalStorage), C2 domains (dobeqnesmot.cc, hjazfioe.surf), API usage anomalies from unexpected geolocations.",
  "initial_access": "Infostealer distribution (method not disclosed); likely traditional vectors",
  "ai_tooling_and_models": [
    "Claude Code",
    "Claude Desktop",
    "ChatGPT Desktop",
    "OpenAI Codex",
    "Cursor",
    "GitHub Copilot",
    "Google Gemini CLI",
    "JetBrains AI Assistant",
    "Kiro IDE",
    "Windsurf",
    "Codeium",
    "Amazon Q"
  ],
  "other_tooling": [
    "Aoki/Aokigahara infostealer",
    "AWS CLI/SSO",
    "Git",
    "SSH"
  ],
  "victims_and_sectors": "Developers using AI coding assistants; scale not disclosed",
  "regions": [
    "unknown"
  ],
  "attribution_or_cluster": "Unknown; no links to existing families; new stealer first seen earlier 2026",
  "scale_and_metrics": "Capability added 2026, expanding; no victim count",
  "prevention_angle": "Rotate AI API keys after compromise; scope keys narrowly; monitor unusual API usage; endpoint protection; credential managers; monitor Aoki C2 domains; file integrity monitoring for AI credential files",
  "related_magicsword_projects": [],
  "source_notes": "OS not specified; other targets suggest Windows; macOS/Linux not confirmed. Detection guidance: monitor AI credential file access, C2 communication (dobeqnesmot.cc, hjazfioe.surf), API usage anomalies from unexpected locations, unauthorized reads of .claude.json, .codex/auth.json, Cursor globalStorage, .copilot/config.json, .gemini/config.json, .aws/credentials, SSH keys.",
  "last_reviewed": "2026-11-04",
  "iocs": {
    "domains": [
      "dobeqnesmot.cc",
      "hjazfioe.surf"
    ],
    "ips": [],
    "hashes": [],
    "urls": []
  },
  "atlas_techniques": [
    {
      "id": "AML.T0055",
      "rationale": "Credential theft targeting AI development tools and cloud credentials",
      "source_urls": [
        "https://www.broadcom.com/support/security-center/protection-bulletin/aoki-infostealer-targets-ai-coding-assistant-credentials"
      ]
    }
  ],
  "attack_flow": {
    "nodes": [
      {
        "id": "deploy",
        "title": "Deploy infostealer",
        "description": "Aoki/Aokigahara deployed (distribution method not disclosed)",
        "kind": "access",
        "source_urls": [
          "https://www.broadcom.com/support/security-center/protection-bulletin/aoki-infostealer-targets-ai-coding-assistant-credentials"
        ]
      },
      {
        "id": "ai-theft",
        "title": "AI credential harvesting",
        "description": "Steals .claude.json, Claude/ChatGPT cookies, Codex config, Copilot/Cursor/Gemini/JetBrains/Kiro/Windsurf/Codeium tokens, AWS creds, Git creds, SSH keys; Cursor state caches chat/code",
        "kind": "ai",
        "source_urls": [
          "https://www.broadcom.com/support/security-center/protection-bulletin/aoki-infostealer-targets-ai-coding-assistant-credentials",
          "https://research.checkpoint.com/2026/infostealer-riding-the-ai-train/"
        ]
      },
      {
        "id": "traditional",
        "title": "Traditional targets",
        "description": "Browsers, crypto wallets, password managers, messaging/gaming, VPN/FTP, email",
        "kind": "execution",
        "source_urls": [
          "https://www.security.com/threat-intelligence/aoki-infostealer-ai-targeting"
        ]
      },
      {
        "id": "exfil",
        "title": "C2 exfiltration",
        "description": "Sends data to C2 (dobeqnesmot.cc, hjazfioe.surf); no backdoor commands",
        "kind": "impact",
        "source_urls": [
          "https://www.security.com/threat-intelligence/aoki-infostealer-ai-targeting"
        ]
      },
      {
        "id": "abuse",
        "title": "Credential abuse",
        "description": "Stolen keys enable acting as developer, LLMjacking, accessing repos/cloud/CI-CD, resale",
        "kind": "impact",
        "source_urls": [
          "https://www.broadcom.com/support/security-center/protection-bulletin/aoki-infostealer-targets-ai-coding-assistant-credentials"
        ]
      }
    ],
    "edges": [
      {
        "source": "deploy",
        "target": "ai-theft"
      },
      {
        "source": "deploy",
        "target": "traditional"
      },
      {
        "source": "ai-theft",
        "target": "exfil"
      },
      {
        "source": "traditional",
        "target": "exfil"
      },
      {
        "source": "exfil",
        "target": "abuse"
      }
    ]
  }
}