Back to skill

Security audit

机关公文排版skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow Word document formatter for Chinese official-document style, and its file access is limited to user-supplied input and output documents.

Install this only if you need Chinese official-document style formatting. Run it on a copy or specify a separate output file, then review the resulting Word document before sending; table formatting may fail on documents with tables because the script references an undefined row_index variable.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

Natural-language instructions, triggers, and usage are presented exclusively in Chinese, which can amount to a language/locale restriction without explicit user opt-in. The file does not state that the skill is region-specific or provide an alternative language option.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The description is written entirely in Chinese and presents the skill as a general-purpose document-formatting tool, but it does not indicate that Chinese language usage is optional or that the skill is intentionally limited to a Chinese government-document context. This can violate language/locale policy when users are not given an explicit language or locale choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file-level description and all user-facing messages indicate the skill is designed exclusively around Chinese-language government document formatting, with no user opt-in or language choice. Under the stated policy, hard-coding a specific language/locale is a finding unless the constraint is explicitly justified as region-specific.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file describes automatic Word-document formatting and shows commands that produce an output document, but it does not explicitly warn users that the tool will write a new file and alter formatting/content structure. Because markdown files should disclose behaviors affecting user data or files, this is a mild missing-warning issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The document specifies Chinese fonts and Chinese-character-based formatting conventions as mandatory rules, which can constitute a language/locale policy constraint in natural-language instructions. The file does not explicitly state that this applies only to a China-specific or Chinese-government document context, nor does it offer an opt-in or alternative locale.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.