ClawHub
Back to skill

Security audit

Fasting Tracker Pro

Security checks for vulnerabilities and agentic risk

Overview

This is a simple fasting advice prompt with optional app-store links and no code, permissions, persistence, or data access behavior.

Review the companion app links before using them, and rely on this skill for general fasting education rather than medical advice, especially if you have diabetes, are pregnant, take medication, or have an eating-disorder history.

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)

Natural-Language Policy Violations

Low
Confidence
91% confidence
Finding
Lines L24-L26 use Hebrew link placeholder text for iOS, Windows, and Android, which imposes a specific language in user-facing instructions. The file does not indicate that Hebrew is optional, localized by user preference, or justified as a region-specific skill.

Static analysis

No suspicious patterns detected.