ClawHub
Back to skill

Security audit

Trash Manager

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed trash-management workflow, but it gives agents broad deletion-routing authority and recommends automatic permanent cleanup without clear user confirmation requirements.

Install only if you are comfortable with agents routing deletions through a shared trash area and, if you configure the cron example, permanently deleting trashed files after 7 days. Before using it broadly, require your agent to ask before trashing important or user-owned files and verify what ~/.openclaw/scripts/trash-manager.sh actually does.

SkillSpector

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 (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill instructs agents to route deletions into a shared trash system with irreversible auto-clean after 7 days, but it does not require an explicit warning or confirmation to the user at the time a file is trashed. In an agentic context, this creates a real risk of users believing deletion is easily reversible when it will later become permanent, especially for destructive actions initiated on the agent's own judgment.

Static analysis

No suspicious patterns detected.