ClawHub
Back to skill

Security audit

Cron Setup Guide Free

Security checks across malware telemetry and agentic risk

Overview

This skill is a mostly coherent cron setup guide, but it grants command execution for persistent scheduled jobs and external delivery with under-scoped invocation guidance and limited consent warnings.

Review this before installing if you do not want an agent to configure persistent scheduled jobs. Use it only for explicit cron setup requests, confirm the exact schedule and command before running it, and verify any Telegram or Discord destination before enabling announce delivery or delete-after-run behavior.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
92% confidence
Finding
The skill is primarily a cron configuration guide, yet it instructs the agent to use shell/network troubleshooting actions such as running ping. That expands behavior beyond documentation into operational command execution, which can cause unintended system or network interactions if the agent follows the guide automatically.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill’s scope description is overly broad and ambiguous, including generic project management and collaboration scenarios unrelated to strict cron setup. This can cause the agent to invoke the skill in unintended contexts, increasing the chance of scheduling, editing, or deleting jobs without sufficiently specific user intent.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The examples demonstrate external-channel delivery and destructive lifecycle actions like auto-delete without prominent warnings or consent checks. In an agent setting, that can lead to unintended data exfiltration to Telegram/Discord or loss of scheduled jobs if examples are operationalized directly.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.