ClawHub
Back to skill

Security audit

Reminder Engine Free

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed one-time reminder helper that uses command execution and session routing for its stated purpose, with some scoping and privacy-notice weaknesses users should understand.

Install only if you want an agent to create one-time reminder cron jobs on your behalf. Before scheduling, confirm the reminder text, time, and destination channel, and avoid using it as a general project-management or team-collaboration skill despite the broad keyword text.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
78% confidence
Finding
The activation/scope text is overly broad and includes unrelated generic keywords such as project management, team collaboration, and performance-adjacent workflow language, which can cause the skill to trigger outside its intended reminder domain. Overbroad routing increases the risk that the agent invokes exec-capable reminder logic in unrelated contexts, exposing session context and command execution pathways when they were not necessary.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The skill explicitly instructs the agent to read deliveryContext.accountId and deliveryContext.to from session_status and use them for message delivery, but it does not provide a user-facing privacy notice or consent boundary for accessing and reusing recipient metadata. In a tool-using agent environment, silent reuse of channel/account routing data can expose or misdirect reminders to unintended recipients if session context is stale, shared, or misunderstood.

Static analysis

No suspicious patterns detected.