ClawHub
Back to skill

Security audit

water-reminder

Security checks for vulnerabilities and agentic risk

Overview

This is a simple reminder skill whose local state and notification behavior are disclosed and aligned with hydration and movement reminders.

Before installing, confirm that 8:00-23:00 GMT+8 is the reminder window you want, and be aware that the skill stores the last reminder time and chat/session ID in a local OpenClaw state file so it can send recurring reminders.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The skill hard-codes a GMT+8 timezone context for reminder timing without obtaining user preference. This can cause reminders to fire at unintended times, potentially disrupting the user or undermining trust in the agent's behavior, especially in cross-timezone environments.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The skill fixes working hours to 8:00-23:00 GMT+8 without documenting user choice or consent. In context this is a reminder skill, so the impact is limited, but rigid scheduling can still cause unwanted notifications during rest time for users in different schedules or regions.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The skill instructs the agent to create and update a local state file automatically, but it does not clearly warn the user that persistent local files will be modified. While this is not overtly malicious, silent persistence can surprise users, affect local state integrity, and normalize unattended filesystem writes by automation.

Static analysis

No suspicious patterns detected.