ClawHub
Back to skill

Security audit

Scheduler Pro

Security checks for vulnerabilities and agentic risk

Overview

This is a locally scoped scheduler/reminder skill with notable reliability and documentation issues, but no evidence of hidden, destructive, credential-seeking, or exfiltrating behavior.

Install only as a simple local task/reminder registry. Do not rely on it for important backups, alerts, reports, or full cron scheduling unless the parser and documentation are fixed and unsupported schedules are rejected clearly.

SkillSpector

Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (2)

Intent-Code Divergence

Medium
Confidence
96% confidence
Finding
The skill advertises cron syntax support and automatic next-run calculation, but the implementation only handles a few minute/hour cases and ignores day, month, weekday, ranges, and step syntax. This mismatch can cause users to rely on schedules that will run at the wrong time or not as intended, which is dangerous for automation tasks such as backups, reports, or reminders.

Intent-Code Divergence

Medium
Confidence
89% confidence
Finding
The examples suggest that tasks will perform real actions like backups, health checks, emails, and reminders, but the code only stores metadata and marks runs. This can mislead operators into believing operational safeguards or maintenance actions are happening when nothing is actually executed.

Static analysis

No suspicious patterns detected.