GEO 多平台内容生成器｜AI-HIVE

• Outcome: Pass
• Latest audit: Aug 25, 2026 · 6:55 AM UTC
• Version: 1.0.0

Overview

This skill is a disclosed AI-HIVE content-generation helper with some activation and API-key storage cautions, but no hidden or destructive behavior was found.

Install only if you intend to use AI-HIVE for content and image-generation workflows. Review parameters before running commands, avoid uploading unlicensed or sensitive media, and remember that init stores an API key locally in a plaintext config file protected by file permissions.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (5)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 89% confidence
• Finding: The skill exposes effective capabilities for environment access, filesystem I/O, shell execution, and network calls without declaring permissions or clearly constraining their use. This is dangerous because users and reviewers cannot accurately assess what the skill may access or execute, increasing the risk of secret exposure, unintended file modification, or arbitrary external requests if supporting scripts are invoked.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 95% confidence
• Finding: The documented purpose is a GEO content-writing workflow, but the underlying behavior reportedly includes account inspection, model enumeration, generic chat, video generation, media upload, and browser-based API-key setup. That mismatch is dangerous because it obscures the real attack surface: a user invoking a content-writing skill may unknowingly trigger broader privileged operations, including credential handling and unrelated remote actions.

Vague Triggers

Medium

• Confidence: 81% confidence
• Finding: The trigger phrases include very broad terms such as FAQ, brand content, and Zhihu answers, which can cause the skill to activate in ordinary conversations not specifically requesting this tool. Overbroad auto-selection is risky because it may route benign user requests into a skill with networked generation and file-handling behavior, increasing the chance of unnecessary data exposure or unintended external actions.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The manifest enables implicit invocation for a skill that can generate production-ready workflows and runnable AI-HIVE commands, but it does not define narrow activation boundaries or exclusions. This increases the chance the agent will invoke the skill in contexts the user did not clearly intend, which can lead to unintended content generation, external API usage, or actions being framed as approved by the user.

Natural-Language Policy Violations

Medium

• Confidence: 83% confidence
• Finding: The default prompt hard-codes Chinese output and a specific production-oriented behavior without indicating user choice or opt-in. While this is not a direct code-execution issue, it can override user expectations, reduce transparency, and cause the agent to steer requests into a predefined workflow that may not match the user’s language or consent preferences.

VirusTotal

65/65 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.