claude-arabic

Fail

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill executes a remote shell script by piping the output of a network request directly into the bash interpreter.
  • Evidence: curl -fsSL https://raw.githubusercontent.com/JamalMohafil/claude-arabic-terminal/main/install.sh | bash in SKILL.md.
  • [REMOTE_CODE_EXECUTION]: The skill executes a remote PowerShell script on Windows systems using the Invoke-Expression (iex) command.
  • Evidence: irm https://raw.githubusercontent.com/JamalMohafil/claude-arabic-terminal/main/install.ps1 | iex in SKILL.md.
  • [COMMAND_EXECUTION]: The skill performs multiple local command executions to manage dependencies and file permissions.
  • Involves running npm install to set up the local repository.
  • Modifies file permissions for binary helpers: chmod +x ~/.claude-arabic-terminal/node_modules/node-pty/prebuilds/*/spawn-helper.
Recommendations
  • HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/JamalMohafil/claude-arabic-terminal/main/install.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Aug 23, 2026, 02:32 PM
Security Audit — agent-trust-hub — claude-arabic