ClawHub
Back to skill

Security audit

Water Reminder

Security checks for vulnerabilities and agentic risk

Overview

This is a simple hydration reminder skill with minor boundary and persistence notes, but no hidden or harmful behavior was found.

Install only if you are comfortable with occasional hydration prompts and, if you use tracking or recurring reminders, make sure memory logging and any cron or heartbeat setup happen only after you explicitly ask for them.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The description says to use the skill when the user 'complains about being thirsty' or 'sets up a daily hydration schedule,' but it does not define clear trigger boundaries or exclusions. These conditions are broad enough to overlap with ordinary conversation and may cause the skill to activate without explicit user intent for a water-reminder workflow.

Vague Triggers

Medium
Confidence
98% confidence
Finding
The condition 'You notice it's been a long time since they took a break' is ambiguous and not clearly tied to explicit user intent, which can cause the skill to activate unexpectedly. In this skill’s context, the effect is limited to unsolicited hydration reminders, so the security impact is low, but it still creates an avoidable boundary violation around autonomy and intent matching.

Static analysis

No suspicious patterns detected.