ClawHub
Back to skill

Security audit

文档工具箱免费版

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local DOCX document-processing helper whose file writes, rendering commands, and temporary artifacts generally match its stated purpose, though its activation wording is too broad.

Install only if you want an agent to create, edit, and render local DOCX files. Use it in a project-specific directory, confirm output paths before edits, clean temporary render files after use, and ignore the broad trigger wording for unrelated coding or deployment tasks.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill advertises document creation, editing, and rendering workflows but does not clearly warn that it will write/modify local DOCX files and generate temporary render artifacts such as PDFs and PNGs. This can lead to unintended overwrites, sensitive document copies persisting in tmp/output paths, and user surprise about local data exposure, especially when handling contracts or internal reports.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger condition is so broad ('需要代码生成、编程辅助、调试测试、开发部署时使用') that it can cause the skill to activate for many generic development requests unrelated to safe DOCX processing. In a skill with read/write/exec permissions, overbroad routing increases the chance the agent will invoke local file modification and command execution in contexts where the user did not clearly intend document-processing side effects.

Content

No source excerpt is available for this finding.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 173)May include surrounding context.

md
brew install libreoffice poppler
# ...
# Ubuntu/Debian
sudo apt-get install -y libreoffice poppler-utils
# ...
# Windows
# 下载LibreOffice安装包，Poppler需单独配置

Static analysis

No suspicious patterns detected.