ClawHub
Back to skill

Security audit

Health Goal

Security checks for vulnerabilities and agentic risk

Overview

This is a simple health-goal coaching skill with no executable code, hidden access, or persistence beyond user-provided progress tracking.

Use this skill for setting and tracking personal health goals. Avoid relying on it for medical diagnosis or treatment decisions, and be mindful that progress logs may include sensitive health information you choose to share.

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 (1)

Vague Triggers

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The description and 'When to Use' section define activation in broad terms such as when users want to 'stay accountable' or ask general progress questions, but they do not clearly distinguish this skill from general health-advice or wellness-chat requests. Without tighter trigger boundaries or exclusion examples, the skill could be invoked for ordinary health conversations that are not specifically about structured goal setting or tracking.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.