ClawHub
Back to skill

Security audit

Book Writing

Security checks for vulnerabilities and agentic risk

Overview

This book-writing skill is a local, markdown-only workflow that stores optional manuscript planning memory on the user's machine and does not show evidence of hidden execution or data exfiltration.

Before installing, be comfortable with the skill keeping concise book-project notes in ~/book-writing/. Do not place secrets or sensitive unrelated personal information there, and delete or disable that folder if you no longer want local manuscript memory retained.

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)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The setup instructs the agent to create and update a persistent local memory file, but the warning to the user is indirect and incomplete. Although the skill says to explain that local project memory can be kept and to ask about auto-activation, it does not clearly communicate retention scope, update behavior, or the privacy implications of writing manuscript-related data to disk, which can lead to unintended persistent storage of sensitive creative or personal information.

Static analysis

No suspicious patterns detected.