Nano Banana Prompt Skill

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:34 PM UTC
• Version:
  1.0.0

Overview

This is a prompt-formatting helper for image generation with broad activation wording, but it does not show hidden access, persistence, credential use, or destructive behavior.

Before installing, be aware that this skill may handle ordinary image-design requests and return Nano Banana-style JSON even when you only wanted casual creative help. Use explicit wording when you want this skill, and review the generated prompt and safety/person-generation parameters before sending them to an image provider.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

High

• Confidence: 94% confidence
• Finding: The skill states that it should trigger whenever a user describes any image they want generated, which makes activation overly broad and likely to intercept many unrelated image requests. In an agent environment, this can cause inappropriate skill selection, override more specialized safeguards or workflows, and lead to unintended prompt transformation without clear user consent.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The trigger list contains broad, common phrases like generating image prompts or posters, but does not define scope boundaries or when the skill should not run. This increases the chance of accidental invocation and can cause the agent to route normal creative requests into a rigid API-parameterization flow the user did not ask for.

VirusTotal

64/64 vendors flagged this skill as clean.