ClawHub
Back to skill

Security audit

Workspace Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed workspace maintenance checklist; it suggests potentially disruptive cleanup actions, but does not hide them or execute them automatically.

Before installing, be aware that this skill may lead the agent to review local OpenClaw workspace files, memory, installed skills, and cron jobs. Treat uninstalling skills, disabling cron jobs, and trimming memory as manual actions that should be confirmed and backed up first.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description is broad enough to match routine, vaguely defined workspace situations such as 'health check' or 'performance tuning,' which can cause the agent to invoke it in many contexts without clear user intent. Because the skill includes audit and maintenance actions that can lead to configuration changes or cleanup recommendations, overbroad triggering increases the chance of unnecessary or unsafe operational changes.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill recommends uninstalling skills, pruning old memory files, disabling cron jobs, and trimming MEMORY.md without an explicit warning, backup step, or confirmation requirement. These actions can remove needed capabilities, destroy historical context, or disable legitimate automation, especially if the skill is invoked during a generic workspace optimization workflow.

Content

No source excerpt is available for this finding.