ClawHub
Back to skill

Security audit

Terminal Mode

Security checks for vulnerabilities and agentic risk

Overview

This skill is a terminal-like file manager whose purpose is clear, but it needs review because it enables broad real file operations with loose activation and incomplete containment.

Review this skill before installing if you do not want an agent mode that can browse, modify, move, copy, change permissions, or delete files. Use it only in a constrained workspace and be careful with absolute paths, ~ paths, rm -f, rm -y, and recursive operations.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill advertises powerful filesystem manipulation capabilities without prominently warning that it can create, modify, move, chmod, and delete user files. In combination with the terminal-like interface, users may underestimate that commands have real side effects, increasing the risk of accidental data loss or unsafe permission changes.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger logic is intentionally broad enough to activate on any mention of “终端” or “terminal,” not just an explicit opt-in request. Because this skill enables filesystem browsing and destructive operations like mv, cp, chmod, and rm, accidental activation can expose files or perform unintended state-changing actions in the wrong conversational context.

Static analysis

No suspicious patterns detected.