ClawHub
Back to skill

Security audit

book-write

Security checks for vulnerabilities and agentic risk

Overview

This skill is a structured novel-writing assistant that asks the agent to manage story planning files and chapter drafts, with no evidence of hidden or destructive behavior.

Install this if you want a strict Chinese-language novel-writing workflow that creates and updates planning and chapter files. Review the proposed file structure and confirmation steps first, especially if you prefer a different language or a lighter writing process.

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)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The activation description includes broad phrases such as '写小说、创作故事、构思情节、塑造人物、撰写章节时激活此技能', which can match many ordinary user requests and cause unintended invocation. This is dangerous because an over-broad trigger can override or interfere with the user's intended workflow, unexpectedly applying rigid file/process rules and changing assistant behavior in contexts where the user did not explicitly ask for this skill.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The skill content is written entirely in Chinese and mandates a fixed operating mode without offering a user language choice. This is risky because it can produce unexpected language switching or inaccessible behavior for users operating in another language, and the rigid instruction set increases the chance the assistant prioritizes skill-local rules over the user's actual communication preferences.

Static analysis

No suspicious patterns detected.