Back to skill

Security audit

Novel Writer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Chinese novel-writing helper, but it asks for recurring automatic file changes and Desktop copying without clear user control.

Install only if you want this skill to manage a specific local Chinese novel project. Before using it, confirm where it may read and write files, disable or explicitly approve any hourly Cron-style automation, and avoid letting it copy files to the Desktop unless you requested that 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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill description claims broad applicability for general novel-writing tasks without clear activation boundaries, making it more likely to trigger on ordinary writing requests and then perform its full workflow. In this skill, that workflow includes local file reads/writes and periodic automation, so over-broad triggering increases the chance of unintended filesystem interaction.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The workflow mandates reading and writing several local manuscript and memory files on every run, yet does not disclose this clearly to the user or obtain consent. Because these files encode persistent state, the skill can silently inspect and alter local content beyond a single response, increasing privacy and integrity risks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill instructs automatic hourly execution with chapter generation, memory updates, outline updates, and copying files to the desktop, but provides no user-facing consent or safeguards. This creates a risk of repeated unauthorized local file modification and propagation of generated content into user-visible locations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The natural-language instructions, title, and workflow are all presented in Chinese, with no indication that users may choose another language. This can be a language policy concern when a skill implicitly forces one locale without user opt-in.

Content

No source excerpt is available for this finding.