ClawHub
Back to skill

Security audit

OpenClaw Cron Setup

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only scheduler skill whose persistent tasks and optional external delivery are disclosed and aligned with its cron setup purpose.

Before installing, treat scheduled jobs as persistent automation: review each job prompt, delivery destination, and retention setting. Avoid sending sensitive summaries to chat channels or webhooks unless the destination is trusted and secured.

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)

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The description text forces a specific language/locale in the skill's natural-language interface and examples without any opt-in or alternative language option. Under the policy, language constraints should be optional or explicitly justified as region-specific.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill explicitly documents a webhook delivery mode that sends task output to an external HTTP endpoint, but provides no warning about data egress, authentication, transport security, or the sensitivity of scheduled task results. In a scheduler skill, jobs may process emails, calendars, health data, or other private content, so silently enabling outbound delivery increases the risk of unintended exfiltration or disclosure.

Static analysis

No suspicious patterns detected.