ClawHub
Back to skill

Security audit

AI大模型专家｜AI电商 Live 图生成｜AI-HIVE MCP

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent workflow guide for creating authorized ecommerce Live Photo assets and does not show hidden execution, exfiltration, or persistence behavior.

Install this if you want a Chinese-language workflow for generating ecommerce Live Photo samples with AI-HIVE. Before using it, make sure the product images are owned or authorized, verify current AI-HIVE model availability and pricing, keep human approval enabled, and do not publish generated assets until rights, brand details, and platform specs have been checked.

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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation description contains very broad trigger terms covering generic AI, ecommerce platforms, and image/video topics, which can cause the skill to activate in many unrelated conversations. Over-broad activation increases the chance the agent injects domain-specific instructions or external-service guidance when the user did not request this workflow, leading to inappropriate routing, confusion, or unsafe tool use in adjacent contexts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill is written to operate in Chinese without offering language negotiation or preserving the user's preferred language. While not directly enabling code execution or data exfiltration, forced language behavior can cause misunderstandings in approval, rights verification, pricing, or platform-spec validation steps, especially in a workflow involving authorization and publishing controls.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.