ClawHub
Back to skill

Security audit

Markdown导出工具

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly describes local Markdown conversion, but it also asks for API credentials and external-service setup without explaining why or where data would go.

Review this skill before installing. It may be suitable for local Markdown conversion, but do not provide API keys, credentials, callback URLs, or sensitive documents unless the publisher clearly explains the remote service used, what data is sent, and how output paths are controlled.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Intent-Code Divergence

High
Confidence
88% confidence
Finding
The skill is presented as a local Markdown conversion tool, yet later sections instruct users to configure API keys, initialize API connections, and call external interfaces without explaining why. This kind of capability mismatch can normalize unnecessary credential collection or outbound communication, increasing the risk of secret exposure or covert data transfer if the skill is followed blindly.

Context-Inappropriate Capability

Medium
Confidence
86% confidence
Finding
Advertising external API integration as a core capability for a Markdown exporter is suspicious because it expands the trust boundary beyond local file conversion without justification. In a skill that also has read, write, and exec tools, undocumented network behavior could expose document contents, metadata, or credentials to third-party services.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The invocation language is overly broad and overlaps with generic productivity and workflow-optimization requests, which can cause the skill to be selected outside its intended Markdown-export scope. Overbroad routing increases the chance that users provide unrelated sensitive data or authorize file/command actions the tool does not strictly need.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill repeatedly instructs users to generate output files, directories, and ZIP artifacts but does not clearly warn about overwrite behavior, destination safety, or filesystem side effects. In a tool with write and exec capabilities, ambiguous path handling can lead to accidental data loss, clobbering of existing files, or writes into sensitive locations if paths are user-influenced.

Static analysis

No suspicious patterns detected.