ClawHub
Back to skill

Security audit

OpenClaw Workspace

Security checks for vulnerabilities and agentic risk

Overview

This skill gives reviewable guidance for auditing and improving an OpenClaw workspace, including memory-related files, without hidden code execution or automatic persistence.

Before installing, understand that this skill may guide your agent to review personal workspace memory and behavior files. That is consistent with its purpose, but you should review proposed diffs before applying them and avoid broad memory indexing unless you want that privacy tradeoff.

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
  • 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
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description and 'When to Use' section repeatedly define activation in very broad terms such as wanting to 'improve or analyze their workspace,' asking 'how to change' behavior, or 'anything equally broad.' This lacks clear constraints or exclusion conditions, increasing the chance the skill is invoked for many ordinary help requests rather than a narrowly defined workspace-audit context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.