ClawHub
Back to skill

Security audit

品牌定位

Security checks for vulnerabilities and agentic risk

Overview

This is a simple brand-positioning guidance skill with no code execution or hidden access, though its activation wording is broad.

Installers should treat this as a lightweight Chinese-language brand-positioning checklist. Review whether the broad trigger phrase is acceptable for your workspace, and make sure any business or personal data used with it is shared intentionally and minimized.

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
  • 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

Low
Confidence
84% confidence
Finding
The description says to invoke the skill whenever performing brand positioning work, but it does not define specific trigger phrases, scope boundaries, or exclusion conditions. This could allow the skill to match a wide range of general business-planning requests rather than a clearly delimited activation context.

Static analysis

No suspicious patterns detected.