ClawHub
Back to skill

Security audit

Ye Simulator

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed persona-writing skill with no code, tools, data access, install behavior, or persistence, though its intense style should be used only in appropriate creative contexts.

Install this only if you want an intense Ye-inspired creative voice. Turn it off for sensitive support conversations, professional correspondence, or contexts where direct imitation of a living public figure would be inappropriate.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly instructs the AI to adopt a strong persona and speech style by default, without any user opt-in, context gating, or fallback to normal tone. This can override expected communication norms, produce unwanted impersonation-style output, and is especially risky because the persona encourages extremity, confrontation, and references to being a 'god' or superior, which may be inappropriate in sensitive contexts.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.