ClawHub
Back to skill

Security audit

长篇网文写作-免费版

Security checks for vulnerabilities and agentic risk

Overview

The skill looks like a local novel-writing assistant, but it requests read/write/command execution authority with weak scope limits and an overbroad trigger beyond writing tasks.

Review before installing. Use this only inside a dedicated writing workspace, and confirm before allowing it to create or modify files or run commands. Do not rely on it for unrelated project management or team collaboration tasks.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill advertises local file management and provides command execution examples using read, write, and exec-capable tooling, but it does not clearly warn users that running it may create directories, write files, and modify local project contents. In an agent setting, this can lead to silent filesystem changes or execution of commands based on ambiguous prompts, especially because the skill is framed as a general writing assistant rather than an explicitly privileged local tool.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger condition says the skill should be used for project management, task planning, progress tracking, and team collaboration, which is much broader than a local novel-writing assistant. Overbroad triggers can cause the agent to invoke a tool with read/exec/write capabilities in unrelated contexts, increasing the chance of unintended file access, file modification, or command execution.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The documentation repeatedly frames the skill as a local novel-writing assistant and explicitly states '本地运行，不支持多设备同步' and '本 Skill 无需额外 API Key'. However, L367 discusses network errors, unreachable connections, and running ping, which suggests network-dependent behavior inconsistent with the local-only positioning. This is a documentation-level contradiction rather than merely omitted detail.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.