ClawHub
Back to skill

Security audit

AI KEY·拿不准的时候

Security checks for vulnerabilities and agentic risk

Overview

This is a decision-coaching skill with disclosed, purpose-aligned local memory use and no executable code or network behavior.

Install this if you want a structured decision-coaching workflow and are comfortable with it saving decision notes and recurring business-pattern observations into the configured AI KEY memory path. Review the broad trigger phrases and Chinese-first interaction style if accidental activation or language mismatch would be disruptive.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger list includes broad, everyday phrases such as '要不要做', '卡住了', and '想不清楚', which are likely to appear in normal conversation outside the user's intent to invoke this skill. That can cause accidental activation, leading the agent to switch into a structured decision workflow unexpectedly and potentially derail or override the intended conversation flow.

Natural-Language Policy Violations

Medium
Confidence
85% confidence
Finding
The instruction to read and follow a Chinese-language interaction spec can force part of the interaction into Chinese-centric behavior without checking the user's language preference. This can cause confusion, reduce user comprehension, and create unsafe misunderstandings if important guidance, choices, or commitments are presented in a language the user did not request.

Static analysis

No suspicious patterns detected.