ClawHub
Back to skill

Security audit

Workspace Structure

Security checks for vulnerabilities and agentic risk

Overview

This skill gives workspace file-placement guidance and does not contain code, hidden execution, persistence, credential handling, or unrelated authority.

Install this if you want consistent workspace organization. Review its folder taxonomy to make sure it matches your preferred workspace conventions, especially because it can steer where new files are saved or moved.

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 (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill’s activation description is broad enough to match many ordinary file-placement or organization tasks without tight boundaries, which can cause the agent to invoke it in contexts where more specific policy or task-focused skills should apply. This is not an exploit by itself, but it increases the chance of misrouting decisions and unintended influence over workspace actions.

Static analysis

No suspicious patterns detected.