ClawHub
Back to skill

Security audit

星月新人助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a static guide that routes users to public Xingyue writing tutorials and does not request sensitive access or run code.

Installers should know this skill is Xingyue-specific and may give Xingyue-centered advice for some broader online-writing or publishing questions. Review the external Bilibili and xingyuexiezuo.com links before relying on current platform, model, or monetization details.

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 (1)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The activation text includes many broad topical triggers such as general writing, publishing, and platform-related terms, which can cause the skill to activate outside narrowly intended contexts. Over-broad routing increases the chance of irrelevant invocation, response hijacking of unrelated user requests, or unintended preference for this skill over safer or more appropriate skills.

Static analysis

No suspicious patterns detected.