ClawHub
Back to skill

Security audit

Training And Nutrition Coach

Security checks for vulnerabilities and agentic risk

Overview

This skill provides fitness planning guidance and a simple local macro calculator without signs of hidden access, persistence, exfiltration, or destructive behavior.

Before installing, consider that the skill may activate for many fitness or meal-planning questions and may ask for personal health-adjacent details such as age, height, weight, sex, activity level, and dietary constraints. Its guidance is framed as estimates and not medical care, so users with injuries, medical conditions, medication-sensitive issues, eating-disorder concerns, or unsafe weight-control behavior should rely on qualified professional advice.

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
Confidence
82% confidence
Finding
The manifest description and opening bullet list define invocation in very broad terms such as 'help with fat loss,' 'muscle gain,' and 'food plan,' which could match many ordinary conversations about health or meals. The file does not provide negative examples or sharper trigger constraints to distinguish when this skill should activate versus when general conversation should continue.

Static analysis

No suspicious patterns detected.