ClawHub
Back to skill

Security audit

Cron Health Monitor

Security checks for vulnerabilities and agentic risk

Overview

This text-only cron monitoring skill is not malicious, but it should be reviewed because it instructs agents to automatically modify, run, reschedule, and even disable cron jobs without clear approval boundaries.

Install only if you are comfortable giving an agent operational control over cron diagnostics and repairs. Before use, set explicit approval rules for cron updates, forced runs, schedule changes, delivery changes, provider/model changes, filesystem writes, and disabling jobs; require logging and a rollback path for every repair action.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The README advertises 'Auto-Repair Delegation' without warning that automated remediation may trigger operationally impactful actions such as restarting jobs, changing schedules, or dispatching repair workflows. In a cron-monitoring skill, users may enable or trust automation without understanding the blast radius, increasing the risk of unintended service disruption or unauthorized changes.

Static analysis

No suspicious patterns detected.