ClawHub
Back to skill

Security audit

Word Docx Tool Free

Security checks across malware telemetry and agentic risk

Overview

This Word document skill is mostly purpose-aligned, but it asks for broad read/write/exec authority and mentions delete/callback-style behavior without clear user controls.

Install only if you are comfortable giving the skill file read/write access and shell-backed execution for document processing. Use it in a limited workspace, review outputs before overwriting files, and avoid using callback URLs or delete-style operations unless the agent asks for explicit confirmation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
87% confidence
Finding
The skill markets itself as a limited free Word-document utility, but the documentation also claims broader operation modes such as delete/export and includes the exec tool. This scope expansion is dangerous because users and hosting agents may grant trust based on a narrower document-editing purpose while the skill can induce more destructive actions than expected.

Vague Triggers

Medium
Confidence
81% confidence
Finding
The sample trigger phrases are extremely broad and overlap with ordinary user language, increasing the chance that an agent invokes the skill unexpectedly. In a skill that can read, write, and execute commands, accidental activation can lead to unintended file creation/modification or command execution without sufficiently explicit user intent.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill exposes read, write, and exec capabilities, but the description does not prominently warn users that it may write files or invoke shell-backed operations. This is dangerous because users may treat it as a simple document helper while it can perform side effects on the filesystem or system environment, increasing the risk of unintended modification or abuse through prompt-triggered actions.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.