ClawHub
Back to skill

Security audit

AI KEY·发布后复盘

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed short-video review skill that reads and updates local content-planning memory, with no evidence of hidden execution, exfiltration, or destructive behavior.

Install this if you want an AI KEY workflow that reviews Douyin/video performance and records lessons into your local content vault. Prefer invoking it explicitly with /aikey-retro, and review proposed memory or tracking-file updates before accepting them because they can influence future content decisions.

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

Medium
Confidence
94% confidence
Finding
The trigger list includes natural-language phrases like '复盘', '数据出来了', and 'why did this video flop/pop' that are broad enough to appear in ordinary conversation. In systems that auto-dispatch skills based on message matching, this can cause unintended invocation, pulling in vault memory and initiating data-collection or file-read behavior without a deliberate user command.

Static analysis

No suspicious patterns detected.