ClawHub
Back to skill

Security audit

Smartwatch Fitness Tracker Buying Consultant

Security checks for vulnerabilities and agentic risk

Overview

This is a pure instruction-based buying guide whose questions are relevant to smartwatch recommendations, with a privacy caution around health and location details.

Before using it, share health, country, and carrier details only at the level needed for a product recommendation. Do not treat smartwatch health features as medical advice, and verify current product specs and regional feature availability before buying.

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 (1)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill explicitly instructs the agent to collect sensitive health details, location/country, mobile carrier, and potentially medical-condition information as part of the buying consultation, but it does not require any upfront privacy notice, data-minimization guidance, or caution against unnecessary disclosure. In a chat setting, this can lead users to overshare special-category personal data that is not strictly necessary for most product-spec recommendations, increasing privacy and compliance risk if the conversation is stored, logged, or reused.

Static analysis

No suspicious patterns detected.