ClawHub
Back to skill

Security audit

Casual Cron

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed reminder scheduler that creates OpenClaw cron jobs, with practical cautions around timezone, recipients, and recurring delivery.

Install only if you want the agent to create OpenClaw cron jobs that can send messages to external channels. Before approving any job, verify the timezone, recipient or channel, message text, recurrence, and whether it is a one-shot job that will delete itself after running.

SkillSpector

By NVIDIA
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 (3)

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The skill hardcodes America/New_York for clock-time scheduling and instructs the agent to compute offsets in that timezone without requiring user confirmation. This can cause reminders to fire at unintended local times for users in other regions, which is especially risky for time-sensitive notifications because the skill is specifically designed to automate message delivery.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The configuration section documents a fixed default timezone policy of America/New_York and does not offer user choice or a per-user default. In a scheduling skill, this increases the chance of systematic misdelivery or missed reminders across users in different locales, making the context more dangerous than a generic documentation issue.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The script always appends --deliver and a destination/channel, producing a ready-to-run outbound messaging command with no confirmation gate, consent check, or destination verification. In this skill context, natural-language input can directly translate into scheduled external messages, which increases the risk of accidental spam, misdelivery, or abuse if invoked on behalf of an unsuspecting user.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.