Back to skill

Security audit

Official Layout Pro(公文专业排版技能包 )

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a legitimate Chinese official-document formatter, but it can read and overwrite caller-selected local files without path containment or overwrite safeguards.

Install only if you trust the environment where it will run. Use explicit input and output paths in a dedicated working folder, avoid running it with broad filesystem privileges, and treat template_name as unsafe until the package validates basenames and prevents overwriting existing files without confirmation.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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
Findings (1)

T05 · Unauthorized Access and Privilege Escalation

Error
Location
main.py:47
Finding

Unrestricted File Access and Template Path Traversal

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The README states that all Chinese uses official document fonts and that all numbers and English characters are forcibly switched to Times New Roman. This imposes a fixed formatting/language convention on mixed-language content without indicating user choice or opt-in, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill is written entirely in Chinese and prescribes Chinese government document formatting conventions and Chinese-specific fonts such as 方正大标宋简体、方正小标宋简体、仿宋_GB2312, without stating that this skill is only for Chinese-language official documents or offering any user language/locale choice. This creates a natural-language locale policy concern because the skill implicitly enforces a specific locale and document standard on all users.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description and function/parameter text are entirely in Chinese and describe formatting according to national official-document standards, but the manifest does not state that the skill is region-specific or that language/locale usage is optional. This can violate language/locale policy where users are not given a choice or explicit notice that the skill is intended only for Chinese-language official documents.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill writes a DOCX file to the user-supplied output path via doc.save(output_path). There is no confirmation prompt, print/log statement, or explanatory docstring/comment warning the user that the operation will create or overwrite a file at the specified location.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.