unity-development

Warn

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to automatically execute a shell command (ls) to inspect specific hidden configuration directories in the user's home folder (e.g., ~/.claude/skills/, ~/.agent/skills/) for environmental discovery.
  • [EXTERNAL_DOWNLOADS]: The agent is mandated to proactively suggest the installation of additional external skills using npx, a command-line tool that fetches and executes code from a remote registry.
  • [DATA_EXFILTRATION]: By performing automated discovery of other installed skills via filesystem inspection, the skill performs reconnaissance on the local environment, identifying other software and tools configured on the user's host system.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 22, 2026, 08:30 PM
Security Audit — agent-trust-hub — unity-development