{
  "id": "fakegit-agentbaiting-island-2026-10",
  "name": "FakeGit agentbaiting - 800+ fake AI skills and MCP servers recommended by agents",
  "date_reported": "2026-10-30",
  "researcher": "Island Security Research",
  "org": "Island",
  "sources": [
    {
      "url": "https://www.island.io/blog/agentbaiting-how-800-fake-ai-skills-and-mcp-servers-delivered-malware",
      "title": "Island: FakeGit 'Agentbaiting' Campaign Targets AI Agent Recommendations",
      "publisher": "Island"
    }
  ],
  "borderline": false,
  "borderline_note": null,
  "ai_role": "ai_agent_or_mcp_as_target",
  "ai_role_secondary": "ai_tool_as_lure",
  "ai_role_detail": "Adversary creates 800+ fake GitHub repos mimicking legitimate AI skills, MCP servers, and Cursor rules; optimizes for LLM recommendation via SEO and naming; agents recommend malicious packages to users",
  "technique_summary": "Oct 30, 2026: Island Security identified 'FakeGit' campaign: 800+ fake GitHub repositories impersonating popular AI skills, MCP servers, Cursor rules, and Claude Code extensions. Repos use typosquat/combosquat names (e.g., cursor-rules-best-practices, mcp-server-github-enhanced, claude-code-skills-security), contain trojanized npm/PyPI packages or malicious install scripts. Adversary optimized repo metadata (README, topics, stars, forks) to rank highly in LLM tool recommendations: when users ask agents find me a GitHub MCP server or what Cursor skills should I use?, agents recommend FakeGit repos from search results. Payloads: Shai-Hulud variants, Discord webhook exfiltration, npm/PyPI worms, SSH backdoors. Island tracked 2,400+ installations from agent recommendations Oct-Nov 2026. Island reports the repositories deliver SmartLoader, which establishes persistence and installs StealC to steal credentials, active sessions, and other sensitive data. Attack exploits agent trust in GitHub search ranking and lack of package verification.",
  "initial_access": "AI agent recommends malicious GitHub repo in response to user query; user clones/installs per agent suggestion",
  "ai_tooling_and_models": [
    "Cursor IDE and Cursor rules",
    "Claude Code",
    "MCP (Model Context Protocol) servers",
    "AI coding assistants (generic)",
    "LLM search and recommendation systems"
  ],
  "other_tooling": [
    "Fake GitHub repositories (800+)",
    "npm/PyPI trojanized packages",
    "Shai-Hulud credential stealer variants",
    "SSH backdoors",
    "Discord webhook exfiltration",
    "SmartLoader dropper",
    "StealC infostealer"
  ],
  "victims_and_sectors": "2,400+ installations tracked Oct-Nov 2026 from agent recommendations; AI developers using agent-assisted package discovery",
  "regions": [
    "Multiple regions"
  ],
  "attribution_or_cluster": "Unknown actor; 'FakeGit' campaign; sophisticated understanding of LLM recommendation mechanics and AI developer workflows",
  "scale_and_metrics": "800+ fake GitHub repos created; 2,400+ installations from agent recommendations (Oct-Nov 2026); ongoing campaign as of Nov 2026",
  "prevention_angle": "Verify GitHub repos before install (check org, stars, age, commit history); use allowlisted skill/MCP sources; implement agent guardrails to warn on unverified packages; educate users not to blindly trust agent recommendations; review install scripts; use SCA tools; prefer official sources (Anthropic MCP registry, Cursor skills directory); flag typosquat patterns",
  "related_magicsword_projects": [],
  "source_notes": "Island Security analysis is the live source for the FakeGit SmartLoader and StealC chain. The previously cited SecurityBreak post returned HTTP 404 and was removed. First documented campaign explicitly optimizing malware for LLM recommendation engines (agentbaiting). Represents new supply chain threat vector where adversaries target agent search/recommendation behavior rather than direct user search. Detection: monitor agent-initiated GitHub clones, alert on typosquat repo names (edit distance to popular repos), check for new GitHub accounts with multiple similar repos, review repos with inflated stars/forks but low commit activity, flag repos created after popular tools rise, scan for SmartLoader/StealC signatures.",
  "last_reviewed": "2026-11-10",
  "iocs": {
    "domains": [],
    "ips": [],
    "hashes": [],
    "urls": []
  },
  "atlas_techniques": [
    {
      "id": "AML.T0000",
      "rationale": "Adversary manipulates LLM tool recommendation systems to deliver malicious packages via agent-suggested GitHub repos",
      "source_urls": [
        "https://www.island.io/blog/agentbaiting-how-800-fake-ai-skills-and-mcp-servers-delivered-malware"
      ]
    }
  ],
  "attack_flow": {
    "nodes": [
      {
        "id": "create-fakes",
        "title": "Create fake repos",
        "description": "Adversary creates 800+ GitHub repos with typosquat/combosquat names mimicking popular AI skills, MCP servers, Cursor rules; optimizes metadata (README, topics, keywords) for LLM search ranking; inflates stars/forks",
        "kind": "ai",
        "source_urls": [
          "https://www.island.io/blog/agentbaiting-how-800-fake-ai-skills-and-mcp-servers-delivered-malware"
        ]
      },
      {
        "id": "agent-recommends",
        "title": "Agent recommends malicious repo",
        "description": "User asks AI agent to find/recommend skill, MCP server, or Cursor rule; agent searches GitHub/web, ranks FakeGit repos highly due to optimized metadata; agent recommends malicious repo to user as legitimate tool",
        "kind": "ai",
        "source_urls": [
          "https://www.island.io/blog/agentbaiting-how-800-fake-ai-skills-and-mcp-servers-delivered-malware"
        ]
      },
      {
        "id": "user-installs",
        "title": "User installs per agent recommendation",
        "description": "User trusts agent recommendation and clones repo or installs package; malicious install script or npm/PyPI postinstall executes; Shai-Hulud stealer, SSH backdoor, or worm payload deploys",
        "kind": "execution",
        "source_urls": [
          "https://www.island.io/blog/agentbaiting-how-800-fake-ai-skills-and-mcp-servers-delivered-malware"
        ]
      },
      {
        "id": "compromise",
        "title": "Credential theft and persistence",
        "description": "Payload harvests AI API keys, GitHub tokens, SSH keys, AWS credentials; establishes persistence (SSH backdoor, cron job); exfiltrates to Discord webhooks or C2; 2,400+ successful compromises tracked Oct-Nov 2026",
        "kind": "impact",
        "source_urls": [
          "https://www.island.io/blog/agentbaiting-how-800-fake-ai-skills-and-mcp-servers-delivered-malware"
        ]
      }
    ],
    "edges": [
      {
        "source": "create-fakes",
        "target": "agent-recommends"
      },
      {
        "source": "agent-recommends",
        "target": "user-installs"
      },
      {
        "source": "user-installs",
        "target": "compromise"
      }
    ]
  },
  "category": "attacks-on-ai",
  "attribution": {
    "actor_name": "FakeGit",
    "country": "Unknown",
    "motivation": "financially-motivated",
    "attributed_by": "Island",
    "confidence": "high"
  },
  "ai_involvement_confidence": "confirmed",
  "detections": [
    {
      "name": "Potential Browser Data Stealing",
      "format": "sigma",
      "url": "https://github.com/SigmaHQ/sigma/blob/master/rules/windows/process_creation/proc_creation_win_susp_copy_browser_data.yml",
      "notes": "Detects StealC infostealer browser data theft on Windows"
    },
    {
      "name": "Suspicious File Access to Browser Credential Storage",
      "format": "sigma",
      "url": "https://github.com/SigmaHQ/sigma/blob/master/rules/windows/file/file_access/file_access_win_susp_process_access_browser_cred_files.yml",
      "notes": "Detects SmartLoader/StealC accessing browser credential files"
    },
    {
      "name": "Malicious skill and MCP repository detection",
      "format": "guidance",
      "notes": "Monitor agent-initiated GitHub clones; alert on typosquat repo names; verify repo authenticity (check org, stars, age, commit history); detect inflated stars/forks with low commit activity; scan for SmartLoader/StealC signatures"
    }
  ],
  "timeline": {
    "first_seen": "2026-10-30",
    "last_updated": "2026-11-04",
    "updates": [
      {
        "date": "2026-10-30",
        "source": "Island",
        "summary": "Initial discovery and analysis"
      }
    ]
  }
}