ClawHub
Back to skill

Security audit

Enlightenment

Security checks across malware telemetry and agentic risk

Overview

This is a text-only spirituality guidance skill with some broad routing examples, but no hidden code, data access, persistence, or destructive behavior.

Installers should understand this skill as spiritual/reflection support, not mental-health care. If using it in an auto-routing system, narrow or clarify the social-media anxiety scenario and ambiguous identity-change trigger so ordinary distress is handled by a more appropriate wellbeing or safety-aware assistant.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
93% confidence
Finding
The Scenario 4 guidance expands the skill from enlightenment-related reflection into generic social-media anxiety management and product recommendations. That scope creep can cause the router to invoke this skill for ordinary lifestyle distress, increasing misrouting and bypassing more appropriate mental-health, coaching, or general-advice skills.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The top-level description includes broad phrases like 'reflective support,' 'describe awakening-like feelings,' and 'inner transformation,' which can overlap with common emotional or self-reflective conversations. In systems that auto-route by semantic similarity, this can capture users seeking general emotional support rather than narrowly scoped enlightenment discussion.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger '为什么有时候感觉自己不像以前那个自己了' is highly ambiguous and commonly appears in everyday identity, stress, depression, trauma, or mental-health conversations. This creates a realistic risk that the skill is invoked for vulnerable users whose issue is not spiritual inquiry, potentially steering them into an ill-fitting interpretive frame.

VirusTotal

56/56 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.