ClawHub
Back to skill

Security audit

Notes Reminders

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent notes and reminders helper, but it can prompt outbound channel messages without clear confirmation or channel controls, and its required scripts are missing from the artifact.

Review this before installing if the agent has access to chat or messaging tools. Use it only where reminder messages should be allowed to post to the specified channels, and verify or add the missing scripts before relying on it.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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 (2)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill instructs the agent to send reminder messages to a channel automatically when reminders fire, but it does not require user confirmation, validate the destination, or warn that this causes outbound messaging side effects. In an agent setting, this can lead to unintended messages being posted to arbitrary channels, causing information disclosure, spam, or disruptive actions beyond simple local note management.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The skill unconditionally interprets relative times in the Asia/Tokyo timezone without checking the user's actual locale or preferences. This can cause reminders to fire at the wrong time, which is a safety and reliability issue that becomes more serious when reminders trigger external messaging actions.

Static analysis

No suspicious patterns detected.