Back to skill

Security audit

Docx Generation

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Chinese-language Word document generation skill that mainly provides formatting guidance and creates a local .docx output file.

Install this if you want a Chinese-language assistant workflow for creating formatted Word documents. Before using it, choose the output filename and location explicitly, and review generated documents before sharing them, especially if they contain personal, business, or contractual content.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (9)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list includes very broad phrases such as common requests to create a Word document, which can cause the skill to activate in routine contexts without clear user intent. Over-broad activation increases the chance the agent will generate files or enter a file-writing workflow unexpectedly, which is a safety and scope-control issue rather than a code-execution flaw.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to save output as a .docx file and later to tell the user the file location, but it does not require prior notice, confirmation, or a safe default save path. In an agent environment, silent file creation can surprise users, overwrite existing files, or place artifacts in unintended locations, especially because the skill frames file output as a normal final step.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file title and core instruction text are entirely in Chinese and present the document-generation requirements as mandatory defaults, with no indication that users may choose another language or locale. This creates a natural-language locale policy issue because it effectively constrains the skill to a specific language without documented opt-in or a region-specific justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file presents all operational instructions and usage guidance exclusively in Chinese. Under the language/locale policy, forcing a specific language without user opt-in or a documented regional justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The document prescribes 黑体、宋体 and Chinese typographic size names such as 小二号、小三号、四号、小四号、五号 as fixed defaults. This is a locale-specific requirement expressed in natural language, but the file does not state that the skill is limited to Chinese-language documents or provide any user opt-in or alternative locale handling.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file is entirely presented in Chinese and does not indicate that users may choose another language or that the skill is intentionally restricted to a Chinese-language context. Under the natural-language policy category, forcing a specific language without user opt-in can be a locale-policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This file’s natural-language instructions and examples are fully Chinese-only, and there is no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

This file contains natural-language instructions and examples exclusively in Chinese, and nowhere indicates that the user can select another language or that the locale restriction is intentional. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This markdown file instructs the skill to save output as a .docx file and choose a save location and filename, which is a user-data-affecting file write operation. The description does not include any warning about overwriting existing files, confirming the destination, or handling sensitive document contents.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.