ClawHub
Back to skill

Security audit

OpenClaw Skill Reviewer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only reviewer guide for checking OpenClaw skills and does not show hidden execution, persistence, exfiltration, or destructive behavior.

This skill appears appropriate for reviewing OpenClaw skills. Before installing, be aware that its example validator path is hardcoded to one user's filesystem and may need adjustment in your environment; also confirm before running any validator or script against skills you do not trust.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/openclaw-specs.md (reported line 21)May include surrounding context.

md
### Safety Rules
- Don't exfiltrate private data
- Don't run destructive commands without asking
- Prefer `trash` over `rm`
- Ask before external actions (emails, posts, etc.)

Static analysis

No suspicious patterns detected.