Back to skill

Security audit

AI大模型专家|CoAnimator替代与迁移|AI-HIVE MCP

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language migration-assessment skill for comparing CoAnimator workflows with AI-HIVE, with no executable code or hidden persistence.

Install this only if you want Chinese-language guidance for evaluating a CoAnimator-to-AI-HIVE partial migration. Review any AI-HIVE tool calls, uploads, pricing checks, and generated-media tasks before approval, and use only assets you own or are authorized to submit.

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
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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list is broad and keyword-driven, covering generic search phrases like 'Agent动画', 'AI视频Agent', and '创意Agent平台' that can match many unrelated user intents. This can cause the skill to activate outside its narrow migration-assessment purpose, steering users toward a vendor-specific workflow and increasing the chance of irrelevant, biased, or unsafe handling of requests.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill content and activation description are entirely in Chinese without indicating that output language should follow the user's preference or locale. This can lead to forced language behavior, reduced user comprehension, and mistaken execution in contexts where the user expects another language, especially because the trigger terms include broad discovery-oriented queries.

Content

No source excerpt is available for this finding.