ClawHub
Back to skill

Security audit

Markdown格式化工具免费版

Security checks across malware telemetry and agentic risk

Overview

This Markdown formatter has a coherent purpose, but it requests broad command execution and file-writing authority without tight boundaries or safeguards.

Review before installing. Use it only on Markdown or text files you intentionally choose, prefer writing to a new output file, and avoid allowing arbitrary shell commands or broad document-conversion requests unless you have inspected the exact command/script being run.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (4)

Context-Inappropriate Capability

Medium
Confidence
94% confidence
Finding
The skill declares `exec` capability even though its stated function is simple Markdown formatting. Unnecessary command execution materially increases attack surface because a prompt-influenced workflow could run local shell commands, touch arbitrary files, or invoke helper scripts beyond pure formatting needs.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger condition 'use when file processing, document conversion, format conversion, content extraction is needed' is overly broad and can cause accidental invocation in unrelated contexts. In a skill with read/write/exec privileges, overbroad routing increases the chance that sensitive files are opened, modified, or processed when the user did not intend to use this tool.

Vague Triggers

Medium
Confidence
81% confidence
Finding
Ambiguous natural-language invocation makes it easier for an agent to infer actions from underspecified prompts and proceed with file operations without sufficient user confirmation. Because the skill can read, write, and execute, vague invocation semantics raise the risk of unintended transformations or command-backed actions on the wrong file.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The documentation explicitly allows direct modification of the original file without a prominent safety warning, backup recommendation, or confirmation requirement. In a formatting tool, in-place writes can destroy user content, especially when paired with ambiguous natural-language triggering and command execution capability.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.