ClawHub
Back to skill

Security audit

Workout

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward workout-tracking command guide with one disclosed destructive profile-delete example that users should handle carefully.

Before installing, understand that the skill helps an agent run workout-cli commands that modify workout records. Profile deletion should be treated as destructive: ask the agent to list profiles and confirm the exact profile name before deleting anything.

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
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly documents workout profile delete old in a multi-user context without any warning, confirmation guidance, or safety checks around deleting another person's profile and workout history. In an agent setting, this increases the risk that the assistant could carry out a destructive command against the wrong profile, causing irreversible loss of another user's data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.