OpenClaw Cron Setup

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:13 PM UTC
• Version:
  1.0.0

Overview

This is a documentation-only skill for configuring OpenClaw scheduled tasks, with disclosed but privacy-sensitive delivery options.

Install only if you want OpenClaw to configure persistent scheduled tasks. Review every job's prompt, schedule, retention, and delivery mode before enabling it; use delivery mode none for private tasks, and avoid sending secrets, personal data, health data, or business-sensitive summaries to chat channels or webhooks.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The skill documents a `webhook` delivery mode that sends task output to an external HTTP endpoint, but it provides no warning about data exfiltration, trust boundaries, or the sensitivity of scheduled task results. In this skill’s context, cron jobs may run autonomously and process emails, calendars, health data, or other private content, so silent support for external POST delivery materially increases the chance of unintended disclosure.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The documentation states that omitting `delivery` defaults to `announce`, which can automatically send task results to a chat channel and summarize them into the main session without any cautionary notice. Because this scheduler supports unattended background execution, a permissive default can leak sensitive outputs to messaging destinations users did not explicitly intend to use.

VirusTotal

64/64 vendors flagged this skill as clean.