Back to skill

Security audit

BookOrigin DOCX Review

Security checks for vulnerabilities and agentic risk

Overview

This skill performs a disclosed local-only DOCX structure preflight and advisory review-package check without network access or document modification.

Install only if a Chinese-language, local DOCX preflight and advisory review workflow fits your use case. The skill still needs access to the DOCX and review JSON files you point it at, but the inspected artifacts do not upload data, modify DOCX files, or create lasting background behavior.

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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file contains user-facing error text in Chinese, such as the argument validation message at L12. Because the CLI consistently presents messages in a single language with no opt-in, fallback, or documented regional limitation, it creates a natural-language locale policy issue under the rule for forced language selection.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Multiple externally visible messages, including failure responses and input/readability errors, are all written in Chinese across these lines. This indicates the skill enforces a single language for interaction rather than offering user choice or clearly documenting a justified locale restriction.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This code contains numerous natural-language messages and boundary descriptions exclusively in Chinese, including thrown error text and returned status text. Under the policy, forcing a specific language without user opt-in or a clearly documented regional justification is a natural-language 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

The self-check constructs a sample document containing Chinese text literals such as '合成教材' and '项目简述'. This bakes in a specific language/locale choice in natural-language content without any opt-in or explanation that the skill is intentionally Chinese-specific.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

This script creates a temporary directory, writes multiple files into it, and then removes that directory recursively in the finally block. Although this is test/self-check behavior, the file itself provides no confirmation prompt, log message, or inline warning before performing file-system writes and deletion.

Content

No source excerpt is available for this finding.

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
selfcheck.mjs:18