Hana Image Gen MacOS

• Outcome: Review
• Latest audit: May 28, 2026 · 8:04 AM UTC
• Version: 1.0.0

Overview

This image-generation skill matches its general purpose, but it needs review because it sends prompts and generated media to external services and downloads API-returned URLs without clear controls.

Install only if you are comfortable sending prompts to OpenRouter/Gemini and generated images to the configured Telegram destination. Use dedicated low-privilege API and bot tokens, avoid sensitive prompts, and review or patch the URL download logic before use.

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• 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
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 94% confidence
• Finding: The skill invokes a Python script with an API key in the environment and performs external network activity, but the manifest declares no permissions or capability boundaries. This is dangerous because agents and reviewers cannot accurately assess what sensitive resources the skill can access or exfiltrate, increasing the chance of unintended data disclosure or unsafe execution in higher-privilege environments.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 92% confidence
• Finding: The documented behavior does not match the actual capability profile: the skill appears to fetch remote content, write files locally, and rely on API-returned paths/URLs beyond the simple 'generate and send image' description. Behavioral mismatch is dangerous because it defeats user consent and review, and hidden file/network operations can expose the host to malicious content retrieval, unsafe file handling, or unexpected data flows.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The workflow sends the prompt to an external image-generation service using an API key but provides no user-facing disclosure that prompt content leaves the local environment. This is dangerous because prompts may contain sensitive or proprietary information, and users are not given informed consent about third-party transmission or retention.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The description states the skill will 'Auto gen & send to Telegram' without specifying what triggers sending, what content may be sent, or whether user confirmation is required. In an agent context, underspecified automatic transmission behavior can lead to unintended disclosure of generated content or prompts to an external service, making this a real security and privacy risk.

Static analysis

No suspicious patterns detected.