Instagram INS 电商图片生成与编辑

• Outcome: Pass
• Latest audit: Aug 17, 2026 · 6:44 AM UTC
• Version: 1.0.0

Overview

This skill is a disclosed AI Hive image-generation helper for Instagram commerce assets, with some unused generic client code that is not exposed through its actual runtime CLI.

Install only if you are comfortable giving AI Hive an API key and uploading chosen product/reference files to its service. Avoid passing private non-image files to the upload or generate inputs, and review the local ~/.ai-hive/config.json key storage if using a shared machine.

SkillSpector

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (6)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 87% confidence
• Finding: The skill invokes a local Python CLI with shell execution, package installation, network access, and file I/O, but does not declare permissions to match those capabilities. This creates a trust gap: users and policy systems cannot accurately assess what the skill can access or modify, increasing the chance of unintended data exposure, filesystem changes, or outbound requests during use.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 94% confidence
• Finding: The documented purpose is narrow image generation for Instagram commerce assets, but the underlying behavior reportedly includes broader chat inference, video generation, account and wallet queries, model enumeration, generic media upload, task lookup, browser-based API key setup, and local credential storage. This mismatch is dangerous because it can conceal a much larger attack surface than users expect, enabling credential capture, sensitive account metadata access, unexpected uploads, and use of unrelated remote capabilities.

Description-Behavior Mismatch

Medium

• Confidence: 97% confidence
• Finding: The file presents itself as an Instagram e-commerce image-generation skill, but actually implements a broad generic AI client with chat, video generation, model enumeration, account inspection, and arbitrary media upload. This capability mismatch violates least-privilege expectations and increases the chance a caller enables functions they did not intend to trust within this skill context.

Context-Inappropriate Capability

Medium

• Confidence: 95% confidence
• Finding: Exposing user account and wallet information is unrelated to Instagram product image generation and creates unnecessary access to sensitive account metadata. In a skill ecosystem, this kind of overbroad functionality can be abused for reconnaissance, billing discovery, or privacy leakage beyond the user’s expected task.

Context-Inappropriate Capability

Medium

• Confidence: 94% confidence
• Finding: General text chat is outside the declared purpose of an Instagram e-commerce image-generation/editing skill. Adding unrelated model interaction expands the attack surface and could let downstream workflows send arbitrary prompts or data to external models under the guise of a narrow image tool.

Context-Inappropriate Capability

Medium

• Confidence: 96% confidence
• Finding: Video generation is materially broader than the advertised image-generation/editing scope. In this context, hidden support for video workflows increases cost, data exposure, and operational risk because users and orchestrators may trust the skill with inputs they would not provide to a more powerful media-generation client.

VirusTotal

65/65 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.