Back to skill

Security audit

Mole Mac Cleanup

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Mac cleanup helper, but users should treat its cleanup, purge, installer, and optimization commands as potentially disruptive and review dry-run output before running them.

Install only if you want an agent to help operate Mole on macOS. Before allowing any non-dry-run cleanup, optimization, purge, installer cleanup, or sudo/Touch ID configuration, review the exact paths and actions, keep backups for important projects, and avoid running broad deletion commands on directories you have not checked.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill documents and encourages execution of cleanup and optimization commands that can delete data and make system-level changes, but it does not provide explicit warnings about permanent deletion, privilege requirements, or the operational risks of actions like resetting services, removing swap files, and rebuilding indexes. In an agent context, this is especially dangerous because concise command examples can be executed mechanically, causing data loss or system instability even if a dry-run is mentioned elsewhere.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The documented purge and installer cleanup features target common user directories and development artifacts such as node_modules, target, venv, Downloads, Desktop, and caches, but the skill does not clearly warn that files may be permanently removed or that detection heuristics may sweep up wanted content. In an agent-operated workflow, this creates substantial risk of deleting important project state, local packages, installers, or user files from broadly scanned locations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.