ClawHub
Back to skill

Security audit

笔记

Security checks for vulnerabilities and agentic risk

Overview

This note-taking skill is not malicious, but it asks for broad local command execution without a clear need or concrete limits.

Review this skill before installing if you do not want a note-taking assistant to have local command-execution authority. File search access is expected for note retrieval, but exec should be removed or tightly documented with specific allowed commands and confirmation requirements.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill declares access to the exec tool but does not clearly warn users that it can execute local commands. In an agent ecosystem, hidden or under-disclosed command-execution capability is dangerous because users or orchestrators may route sensitive tasks to the skill without understanding that it can run system commands, increasing the risk of unsafe execution, data exposure, or abuse if later prompts steer it toward shell use.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.