ClawHub
Back to skill

Security audit

laolei novel writer

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent novel-writing skill that creates and updates story project files, with only minor routing and language-disclosure concerns.

Before installing, note that this skill is best suited for multi-chapter novel projects and may activate on broad story-writing prompts. It will guide the agent to create and update local Markdown files for the novel, so use it in a workspace where those project files are expected.

A.I.G

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

SkillSpector

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The activation examples are generic writing requests such as 'help me write a story' and 'write a ... novel,' which can overlap with ordinary assistant usage and cause unintended skill invocation. In an agent framework, overbroad triggers can redirect normal user requests into this skill unexpectedly, affecting routing reliability and potentially causing unnecessary file-oriented behavior or context handling the user did not request.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The manifest description presents the skill in both Chinese and English, but the rest of the instructions are written entirely in Chinese and do not state that users may choose their preferred language. This can create an implicit language expectation without explicit opt-in or a documented locale constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.