ClawHub
Back to skill

Security audit

顺序阅读工具-免费版

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local long-form reading and note-taking helper whose file reads and Markdown note writes match its stated purpose.

Install this if you want an agent to read user-selected long documents and create local Markdown notes. Be mindful that using it may read document contents into the agent context and write notes or progress files to the output path you provide or the documented default.

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 (3)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill states that natural-language user instructions can trigger tool actions automatically, but the trigger description is broad enough to overlap with ordinary reading or study requests. In an agent environment with read/exec/write capabilities, this can cause unintended activation and file operations when the user did not clearly consent to running the skill.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The keyword list contains very generic terms like study, notes, knowledge, analysis, and automation that could match many unrelated prompts. This increases the chance of accidental skill selection and unintended use of its write or exec tools, especially in multi-skill agent environments where routing is prompt-driven.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill advertises local note saving and includes the write tool, but it does not clearly warn users that it may create or modify files on disk as part of normal use. In practice, a user could trigger the skill expecting analysis only and unknowingly cause persistent file writes, overwrites, or storage of sensitive document content.

Static analysis

No suspicious patterns detected.