Back to skill

Security audit

Word Template Filler

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it claims by filling local Word templates, with one unsafe manual debugging command users should avoid.

Install only if you are comfortable running Word automation on local .docx files on Windows. Avoid the documented `taskkill /f /im WINWORD.EXE` debug step unless all Word documents are saved and you intentionally want to close every Word process.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The documentation recommends taskkill /f /im WINWORD.EXE, which forcibly terminates all running Word processes on the system, not just the instance started for this skill. This can cause loss of unsaved user work and disrupt unrelated Word sessions, making it an unsafe operational instruction even though it is framed as a debugging step.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest sets the skill language to "zh-CN", which is a locale-specific constraint expressed in natural language metadata. There is no indication here that users can opt into another language or that the restriction is justified by a region-specific purpose.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.