ClawHub
Back to skill

Security audit

cron-quickstart

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only cron quickstart skill whose scheduled-agent behavior is disclosed and aligned with its purpose.

Before installing, understand that this skill teaches agents how to create cron jobs that can run later or inject session events. Use it only for jobs you intentionally schedule, prefer isolated sessions for autonomous work, and remove recurring jobs you no longer need.

SkillSpector

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 (1)

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The skill explicitly enables scheduled autonomous actions and system-event injection into sessions, but it provides no warning about background execution, possible session-side effects, or the trust implications of injecting text as a system event. In an agent environment, this can lead users to create jobs that later act without contemporaneous confirmation, increasing the risk of unwanted actions, confusing behavior, or prompt-context manipulation across sessions.

Static analysis

No suspicious patterns detected.