Back to skill

Security audit

cron-quickstart

Security checks for vulnerabilities and agentic risk

Overview

This is a short quickstart guide for OpenClaw cron scheduling, with no bundled code, scripts, or hidden behavior.

Before installing, treat this as guidance for creating cron jobs that may run in the future. Prefer isolated sessions for autonomous checks, use deleteAfterRun for one-time reminders, review recurring jobs periodically, and replace example times and timezones with your own.

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
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly enables scheduled agentTurn execution and systemEvent injection into sessions, but it does not warn that these actions can run later without an immediate user checkpoint and can automatically affect session state. In a scheduling skill, deferred autonomous execution is the core capability, so omitting safety guidance increases the chance of misuse, unintended actions, or persistence of harmful prompts across sessions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill includes cron examples that force a specific locale/timezone setting, which can bias outputs or schedules toward one region without user opt-in. There is no accompanying explanation that the skill is region-specific or instruction to choose a timezone appropriate to the user.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This example repeats a fixed locale/timezone choice that may cause users to adopt an unintended regional setting. Because the file does not offer alternatives or explain a region-specific purpose, it presents a natural-language locale policy concern.

Content

No source excerpt is available for this finding.