ClawHub
Back to skill

Security audit

My Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only test utility skill with broad local file-management wording but no executable code, install hooks, persistence, or hidden behavior.

Install only if you are comfortable with a small test skill that may guide an agent on local text, files, and workflow tasks. Keep use scoped to the intended workspace and require explicit confirmation before any file writes, moves, deletes, or broad automation.

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
86% confidence
Finding
The skill explicitly states it can 'manage local files' but provides no warning, limitation, or consent requirement around reading, modifying, or deleting user files. In an agent context, vague file-management capabilities increase the risk of unintended or unauthorized file operations, especially if the model invokes the skill without clear user awareness of side effects.

Static analysis

No suspicious patterns detected.