hud

Fail

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill establishes persistence by instructing the agent to modify ~/.claude/settings.json to register a statusLine command. This ensures the custom script omc-hud.mjs is executed automatically on startup and periodically during use.
  • [REMOTE_CODE_EXECUTION]: The generated omc-hud.mjs script performs dynamic code loading using asynchronous import(). It attempts to load and execute code from paths computed at runtime, including development directories and the oh-my-claudecode npm package.
  • [COMMAND_EXECUTION]: The setup procedure employs several node -e shell commands to automate directory creation, file system verification, and the modification of file permissions to make scripts executable.
  • [EXTERNAL_DOWNLOADS]: The skill references and depends on the oh-my-claudecode npm package. The configuration script is designed to dynamically fetch and execute this package if found in the environment or registry.
  • [DATA_EXFILTRATION]: The instructions require the agent to read the full contents of ~/.claude/settings.json. This access exposes potentially sensitive application configuration and session data to the agent's context.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Apr 11, 2026, 09:20 AM