ClawHub
Back to skill

Security audit

OpenClaw Workspace Auditor

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed read-only local workspace auditor that reports issues without modifying files or sending data out.

Install only if you want an agent to inspect your current OpenClaw workspace and summarize structure, progress, memory, knowledge-base, and temporary-file issues. The main thing to check is that you invoke it on the intended workspace path, since it is designed to traverse workspace files for reporting.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill clearly instructs the agent to inspect the local workspace and run a Python scanner, which implies file-read capability, yet no explicit permissions are declared. This creates a transparency and governance gap: users or policy systems may not realize the skill can traverse and read workspace contents, increasing the risk of unintended data exposure during use.

Vague Triggers

Medium
Confidence
81% confidence
Finding
The trigger list includes broad phrases like “审计” and “健康检查,” which can match many unrelated user intents and cause the skill to activate unexpectedly. Over-broad activation is dangerous because it may initiate workspace scanning in contexts where the user did not specifically consent to filesystem inspection.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.