Back to skill

Security audit

Hydration Tracker

Security checks for vulnerabilities and agentic risk

Overview

This hydration tracker only stores simple water-intake data locally and does not show hidden network, credential, or destructive behavior.

Before installing, be aware that this skill will create persistent local files under ~/.water_reminder for your hydration history and goal. It does not appear to contact external services, but its reminder feature is just a manually invoked tip, not automatic scheduled reminders.

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
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The skill description promises reminders, but the documented behavior only prints a tip when manually invoked, and it also omits disclosure that it persists data in the user's home directory. This mismatch is dangerous because users may trust inaccurate claims about functionality and storage behavior, leading to uninformed use of persistent local data access and reduced ability to assess privacy implications.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill declares no explicit tool scope or permissions while its documented behavior includes reading environment-related paths and performing persistent local file reads/writes under ~/.water_reminder. This is dangerous because it hides actual capabilities from users and reviewers, weakening informed consent and policy enforcement even if the current functionality appears limited to hydration data.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The command table says info shows version info (v1.0.0), but the manifest declares version 2.0.0 at L004 and the changelog also labels 2.0.0 as the current release at L060-L063. This is an active documentation contradiction about what the skill reports.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.