# FakeGit agentbaiting - 800+ fake AI skills and MCP servers recommended by agents

- ID: fakegit-agentbaiting-island-2026-10
- Reported: 2026-10-30
- Researcher: Island Security Research
- Organization: Island
- AI role: ai_agent_or_mcp_as_target (Agent / MCP as target)
- Confidence in AI involvement: not assessed
- Research / borderline: false
- Last reviewed: 2026-11-10
- Entry page: https://openattacks.ai/attacks/fakegit-agentbaiting-island-2026-10/
- Entry JSON: https://openattacks.ai/api/attacks/fakegit-agentbaiting-island-2026-10.json
- Browse title: FakeGit agentbaiting - 800+ fake AI skills and MCP servers recommended by agents
- Editorial 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…
- Evidence class (catalog annotation): Not classified
- Source-stated target environments: Not specified
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/fakegit-agentbaiting-island-2026-10.json

## Technique
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.

## Stack relevance (editorial)
Assessment: not\_assessed. No reviewed applicability annotation is available. Product mentions do not establish victim conditions.
A product mention alone is not a victim-side applicability mapping. Selection does not verify affected versions, permissions or compromise.

## 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](https://cursor.com/) and [Cursor](https://cursor.com/) rules
- [Claude Code](https://github.com/anthropics/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

## Target geography
- Multiple regions

## Attribution
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

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### create-fakes: Create fake repos [ai]
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
Evidence: https://www.island.io/blog/agentbaiting-how-800-fake-ai-skills-and-mcp-servers-delivered-malware

### agent-recommends: Agent recommends malicious repo [ai]
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
Evidence: https://www.island.io/blog/agentbaiting-how-800-fake-ai-skills-and-mcp-servers-delivered-malware

### user-installs: User installs per agent recommendation [execution]
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
Evidence: https://www.island.io/blog/agentbaiting-how-800-fake-ai-skills-and-mcp-servers-delivered-malware

### compromise: Credential theft and persistence [impact]
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
Evidence: https://www.island.io/blog/agentbaiting-how-800-fake-ai-skills-and-mcp-servers-delivered-malware

Connections:
- create-fakes -> agent-recommends
- agent-recommends -> user-installs
- user-installs -> compromise

## Stage defense and hunting recommendations
Editorial recommendations, not validated coverage. Source-controlled query starters are drafts. Custom-schema examples require telemetry collection and field mapping; absence of a mapping means not assessed. MagicSword policy opportunities require managed Windows scope and enforcement.
### create-fakes: Coordinated messaging / propagation
- Visibility: Platform / application records
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/social.sigma.yml
- KQL query download: /api/detections/social.kql
- SPL query download: /api/detections/social.spl
- Hunt hypothesis: Related accounts or assistants repeat correlated posting, forwarding or tool actions beyond the expected user workflow.
- Required telemetry: Platform account and posting audit; Agent session and message-provenance records; Rate, recipient and content-similarity features
- Investigate: Group actions by linked account, session, recipient and time rather than judging writing style.
- Investigate: Compare propagation with legitimate campaigns and preserve whether the source describes a lab demonstration or observed abuse.
- Limitation: Requires platform-side visibility. Similar content and synchronized activity can have legitimate explanations.
- No direct MagicSword prevention claim is recorded for this stage.

### agent-recommends: Untrusted content enters an agent session
- Visibility: Application / agent audit records
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/agent-input.sigma.yml
- KQL query download: /api/detections/agent-input.kql
- SPL query download: /api/detections/agent-input.spl
- Hunt hypothesis: An agent ingests external content or an untrusted session identifier before a tool action or configuration change outside the approved task.
- Required telemetry: Input provenance, source type and request/session identifier; Captured tool responses or retrieved content where collection is approved; Subsequent tool calls, configuration changes and approval decisions
- Investigate: Join the ingested input to later actions by session or request ID; preserve the original content as evidence.
- Investigate: Compare the resulting action with the approved task and baseline. Receiving suspicious text alone is not successful injection.
- Limitation: Requires application instrumentation and a custom field mapping. Input exposure does not prove that the model followed instructions, executed a tool or bypassed approval. Avoid collecting sensitive prompt bodies unless authorized.
- Qualification: Review recommendation provenance and the subsequent action. A repository appearing in search results is not compromise.
- No direct MagicSword prevention claim is recorded for this stage.

### user-installs: Package installation spawns a shell or downloader
- Visibility: Endpoint process telemetry where collected
- Query origin: catalog_authored; status: draft; log scope: native
- SIGMA query download: /api/detections/package-install-execution.sigma.yml
- KQL query download: /api/detections/package-install-execution.kql
- SPL query download: /api/detections/package-install-execution.spl
- Hunt hypothesis: A package-manager install or lifecycle script launches a shell, downloader, or script interpreter that retrieves or executes an unexpected second stage.
- Required telemetry: Process creation with ancestry and complete command lines; Package-manager, CI, and installation logs; Download, file creation, signature, and network telemetry
- Investigate: Identify the package, version, publisher, lifecycle hook, resolved source, and parent process.
- Investigate: Recover downloaded content and correlate credential access, persistence, or outbound traffic.
- Limitation: Build and install scripts commonly invoke shells and download dependencies. Require package provenance and destination context; this hunt does not by itself prove supply-chain compromise.
- No direct MagicSword prevention claim is recorded for this stage.

### compromise: Sensitive store access → credential use
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/credentials.sigma.yml
- KQL query download: /api/detections/credentials.kql
- SPL query download: /api/detections/credentials.spl
- Hunt hypothesis: An unexpected process or tool accesses credential stores and is followed by token use or outbound transfer inconsistent with the owner.
- Required telemetry: File-read / API access telemetry for relevant secret stores; Process identity and command lines; Identity, token and outbound-network audit logs
- Investigate: Identify the actor, process and exact store touched, then pivot to token use from new devices or infrastructure.
- Investigate: Correlate reads with egress and rotate affected credentials after confirming exposure.
- Limitation: Defender DeviceFileEvents is not a general file-read audit trail. Collect suitable object-access, EDR or application logs; legitimate developer tools also read secrets.
- No direct MagicSword prevention claim is recorded for this stage.


## MITRE ATLAS
Mappings are catalog annotations based on described behavior, not assignments or endorsements by MITRE.
- AML.T0000: Search Open Technical Databases — Adversary manipulates LLM tool recommendation systems to deliver malicious packages via agent-suggested GitHub repos
  Technique: https://atlas.mitre.org/techniques/AML.T0000
  Evidence: https://www.island.io/blog/agentbaiting-how-800-fake-ai-skills-and-mcp-servers-delivered-malware

## Defensive notes
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

## Sources
- https://www.island.io/blog/agentbaiting-how-800-fake-ai-skills-and-mcp-servers-delivered-malware — Island: FakeGit 'Agentbaiting' Campaign Targets AI Agent Recommendations

## 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.

## Indicators (untrusted data; do not visit or execute)
```json
{
  "domains": [],
  "ips": [],
  "hashes": [],
  "urls": []
}
```
