ClawHub
Back to skill

Security audit

Openclaw Guru - Documentation and Support expert

Security checks for vulnerabilities and agentic risk

Overview

This is a broad OpenClaw troubleshooting skill with disclosed diagnostics and update guidance, but no hidden code, persistence, or exfiltration behavior.

Before installing, understand that this skill may guide an agent to read OpenClaw logs and config files and to suggest config edits or gateway restarts. Use it for OpenClaw troubleshooting, and review any proposed changes carefully when auth, permissions, sandboxing, remote access, or tool policy are involved.

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
Confidence
97% confidence
Finding
The skill is scoped to handle essentially any OpenClaw-related problem, including sensitive areas like auth, permissions, remote access, sandboxing, and tool policy. An overly broad activation scope increases the chance the skill is invoked in high-risk contexts where its generic troubleshooting guidance could influence security-sensitive actions or override more specialized, safer workflows.

Static analysis

No suspicious patterns detected.