ClawHub
Back to skill

Security audit

Markdown 工具箱专业版

Security checks for vulnerabilities and agentic risk

Overview

This Markdown toolkit is broadly aligned with documentation work, but it asks for command execution and file-writing authority without tight scoping or clear user control.

Review this skill before installing if you use it in sensitive repositories. It appears intended for Markdown documentation automation, but you should only let it run commands or write files for explicit documentation tasks, preferably within a limited docs directory, and confirm any export, delete, global install, network check, or bulk rewrite action first.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill advertises both exec and write capabilities for a Markdown toolkit, but the documentation does not constrain command scope to specific binaries, directories, or safe argument patterns. In an agent setting, this broad execution surface can let routine documentation requests trigger arbitrary shell commands or filesystem changes beyond what users reasonably expect from Markdown processing.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The trigger condition is broad enough to match ordinary file handling, conversion, and content extraction tasks, which increases the chance the agent invokes a skill with write/exec powers in contexts where a safer read-only skill would suffice. Over-broad activation expands the attack surface and can lead to unintended command execution or file modification during common documentation workflows.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill declares write and exec capabilities but does not prominently warn users that it may modify files, generate outputs, or run local commands. In agent environments, this mismatch between perceived and actual behavior can cause users to authorize documentation assistance without understanding the filesystem and execution risks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.