ClawHub
Back to skill

Security audit

Nano Banana 2 — Pro Pack on RunComfy

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed RunComfy image-generation helper with one routing caveat: its trigger phrase for “Gemini image” is broader than the specific Nano Banana 2 model.

Install only if you are comfortable sending image prompts to RunComfy and using a RunComfy token. Be aware that generic “Gemini image” wording may activate this Nano Banana 2 skill, so confirm the intended model/provider before generating, especially for sensitive prompts or paid runs.

SkillSpector

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 (1)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger text includes broad activation language such as matching any mention of 'Gemini image' or any explicit ask to generate with Nano Banana, which can cause the skill to activate outside its narrow intended scope. Over-broad routing can mis-handle user requests, invoke an external paid/image-generation service unexpectedly, and increase the chance that untrusted prompts or sensitive content are sent to a third party without clear user intent.

Static analysis

No suspicious patterns detected.