ClawHub
Back to skill

Security audit

Openclaw Automation Guide

Security checks for vulnerabilities and agentic risk

Overview

This is a simple OpenClaw automation guide, but it encourages automatic publishing, forwarding, email, file, and payment-webhook workflows without enough safety scoping.

Review this carefully before installing or adapting it. Do not enable the publishing, forwarding, email, webhook, or file-processing examples until you have limited the accounts and folders involved, tested with dry runs, authenticated webhooks, added rate limits/logging, and required human review for outward-facing or financial actions.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill promotes scheduled and triggered automations that can send emails, publish content, forward messages, and process payment/error webhooks without any warning about human review, authorization, rate limiting, or the consequences of acting on external input. In an automation-focused skill, omission of consent and safety guidance materially increases the risk of unintended data disclosure, unauthorized actions, spam, or destructive task execution.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
72% confidence
Finding

The visible user-facing description and instructions are entirely in Chinese, and the skill does not state that it is region-specific or provide any language choice. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy issue when no justification or alternative is provided.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.