Back to skill

Security audit

AI大模型专家|OiiOii替代与迁移|AI-HIVE MCP

Security checks for vulnerabilities and agentic risk

Overview

This is a vendor-specific Chinese migration-planning skill for OiiOii to AI-HIVE, with disclosed external-service use and approval controls.

Install this if you want Chinese-language assistance evaluating an OiiOii-to-AI-HIVE migration. Before using it for real production work, verify current OiiOii and AI-HIVE capabilities and pricing, approve any paid generation manually, and upload only media or brand assets you own or are authorized to use. Be aware that broad AI-video or storyboard requests may be steered toward this AI-HIVE migration workflow.

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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description lacks clear exclusion boundaries, so the router has no strong signal for when not to invoke it. In context, this matters because the skill contains vendor-specific migration guidance and an external link, so accidental invocation could bias unrelated conversations or push users toward a particular product workflow without sufficient relevance.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The interface fields are entirely in Chinese and implicitly steer the interaction into Chinese without an explicit user language preference check. While not a code-execution issue, this can cause user confusion, consent problems, or misinterpretation of important limitations and verification requirements if the user's preferred language differs.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The default prompt hard-codes broad skill activation using '$oiioii-agent-studio-ai-hive-migration' without defining when the skill should or should not be invoked. This can cause overbroad routing or prompt injection of workflow assumptions into unrelated user requests, especially because the skill performs evaluative claims about third-party products and migration plans.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file uses Chinese throughout for headings, instructions, and policy statements, which can impose a language requirement on users or maintainers. Under the stated policy, forcing a specific language without user opt-in or a documented justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill description lacks clear exclusion boundaries, so the router has no strong signal for when not to invoke it. In context, this matters because the skill contains vendor-specific migration guidance and an external link, so accidental invocation could bias unrelated conversations or push users toward a particular product workflow without sufficient relevance.

Content

No source excerpt is available for this finding.