Skills
skills/aradotso/claude-code-skills/free-claude-code-ai-desktop-app/Gen Agent Trust Hub

free-claude-code-ai-desktop-app

Fail

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs users to download a binary archive from https://github.com/anthropic-claude-code-ai/free-claude-code-ai-desktop-app/releases/download/claude-code/free-claude-app.zip. The GitHub organization anthropic-claude-code-ai is not an official Anthropic repository and appears to be a typosquatting attempt to impersonate the legitimate brand.
  • [REMOTE_CODE_EXECUTION]: The provided instructions guide the user through downloading, extracting, and executing an unverified executable file (ClaudeCodeAI.exe) from an untrusted remote source.
  • [COMMAND_EXECUTION]: The skill utilizes PowerShell commands (Invoke-WebRequest, Expand-Archive, Start-Process) to automate the installation and execution of external code.
  • [COMMAND_EXECUTION]: The skill explicitly instructs the user to execute the application with administrative privileges (-Verb RunAs). Granting elevated permissions to an untrusted binary downloaded from an impersonating domain allows for total system compromise.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jun 17, 2026, 06:51 PM
Security Audit — agent-trust-hub — free-claude-code-ai-desktop-app