ClawHub
Back to skill

Security audit

Essence Trace

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only Chinese reasoning skill for root-cause analysis, with no evidence of code execution, data access, persistence, or hidden behavior.

Install this if you want a Chinese-language root-cause and first-principles reasoning template. Be aware that its generic 'why' trigger may activate more often than expected, and non-Chinese users may find it hard to use without translation.

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 (4)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger list includes extremely broad everyday language such as '为什么' ('why'), which can cause the skill to activate on a large fraction of normal conversations. Over-broad activation can hijack routing, override more appropriate skills, and create denial-of-intent behavior where users are pushed into this reasoning workflow unexpectedly.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger table marks broad natural-language patterns like '为什么这么说' and '我想搞明白 [现象/观点/问题]' as unconditional activators without strong constraints. In an agent ecosystem, this increases unintended invocation risk, causing context misrouting and making the skill disproportionately influential relative to user intent.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The skill content is entirely in Chinese and presents fixed Chinese trigger words and output structure without offering any user choice, fallback language, or documented locale requirement. This can exclude or mislead users who do not read Chinese, causing incorrect use of the skill or inaccessible guidance, but it does not create a direct code-execution or privilege-escalation risk.

Static analysis

No suspicious patterns detected.