ClawHub
Back to skill

Security audit

Word Automation

Security checks for vulnerabilities and agentic risk

Overview

This is a local Word/WPS document automation skill with clear file-writing capabilities, some documentation scoping gaps, and no evidence of hidden network access, credential use, persistence, or destructive behavior.

Use this skill only with documents and output paths you intentionally choose. Prefer saving to new filenames or a dedicated output folder, especially for replace, headings, header-footer, page-break, merge, split, and export operations. Be careful exporting or splitting sensitive documents because derivative files may contain the same private content.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The skill description does not accurately match the documented behavior: it claims single-document use while exposing multi-document merge capability, and it promises image replacement though only insertion is described. This mismatch is dangerous because users and orchestrators may underestimate the scope of file operations, leading to unsafe invocation, incorrect trust decisions, or accidental bulk data modification.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill documents file-modifying behavior and output generation, but it does not declare any explicit tool scope or permission boundaries. This is dangerous because an agent may invoke document-writing actions without clear policy constraints, increasing the risk of unintended file modification or data overwrite on the host system.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest says the skill is limited to single-document actions, but the documented commands include merge and split workflows that operate on multiple files or produce multiple outputs. This is dangerous because the declared safety boundary is misleading, which can cause agents to permit broader filesystem impact than intended.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill omits safety warnings despite supporting document modification, export, split, merge, and file creation. Without clear warnings, users may not realize that running these commands can overwrite documents, create derivative files, or expose sensitive content through exports, increasing the chance of accidental data loss or leakage.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This code saves modified or generated documents to disk via doc.SaveAs(...), and the save helper is used by multiple commands that alter user files. The file contains no confirmation prompt, user-facing log/print, or explanatory comment/docstring warning that these operations will write output documents, so the write behavior is undisclosed within this code file.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

cmd_split creates directories with mkdir(...) and writes multiple output documents into that directory, which can materially change the filesystem. There is no confirmation, user-facing notice, or explanatory comment in this file disclosing that the command will create directories and emit multiple files.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.