mole-cleaner

Fail

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill instructions in SKILL.md and the diagnostic script scripts/mole-check.sh contain commands that download a shell script from a remote URL (https://raw.githubusercontent.com/tw93/mole/main/install.sh) and pipe it directly into bash. This pattern executes arbitrary remote code without integrity checks or user inspection of the script content before execution.
  • [COMMAND_EXECUTION]: The skill enables the agent to perform extensive system modifications using the mo command-line utility. This includes deep system cleaning, application uninstallation (deleting files across multiple system directories), and system optimization tasks like rebuilding Launch Services and Spotlight indexes. While the skill mandates a 'Scan → Show → Confirm → Execute' workflow, the underlying capability for broad file system deletion remains high-risk.
  • [PRIVILEGE_ESCALATION]: The skill includes commands to modify system security settings, specifically mo touchid, which configures Touch ID for sudo authentication. It also notes that system cache cleaning may require sudo permissions, granting the agent the ability to request elevated privileges.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of third-party software from external sources (Homebrew and direct GitHub downloads) that are not part of the platform's trusted vendor list.
Recommendations
  • HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/tw93/mole/main/install.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Aug 16, 2026, 12:30 AM
Security Audit — agent-trust-hub — mole-cleaner