nano-banana-2

Name: runcomfy-agent-skills/nano-banana-2
Author: agentspace-so

Share on X Share on LinkedIn Share on Bluesky

40Medium

The skill executes unpinned and unverified packages via npx, creating a critical supply chain vulnerability that allows for the arbitrary execution of malicious or compromised code at runtime.

ThreatsCI SM CS BC S HITL

Threat Analysis

AI Agent Traps ↗Scanned 7/3/2026

Content InjectionPerceptionclean

Semantic ManipulationReasoningclean

Cognitive StateMemory & Learning2 findings

Behavioural ControlActionclean

SystemicMulti-Agent Dynamicsclean

Human-in-the-LoopHuman Overseerclean

Skill Info

Nameagentspace-so/runcomfy-agent-skills/nano-banana-2

Registrygithub

Versionfca19ae084c2

PURLpkg:github/agentspace-so/runcomfy-agent-skills@fca19ae084c2?skill=nano-banana-2

Stars27

Installs336,900

Source

Repository ↗SKILL.md ↗

Install

This skill has findings worth reviewing before installing.

GitHub

336,900 installs

Skills.shDocs

npx skills add https://github.com/agentspace-so/runcomfy-agent-skills

Assessments (1)

AI Agent Traps ↗

Unpinned npx package execution — `npx <pkg>` without a version pin pulls latest from npm at runtimemediumsupply chainAML.T0010AML.T0019AML.T0058LLM03:2025

Unpinned npx package execution — `npx <pkg>` without a version pin pulls latest from npm at runtime

95% confidenceline 28

npx skills

Global/unverified dependency execution — global npm/yarn package, dotnet tool, or auto-confirmed npx run without version or integrity pinningmediumsupply chainAML.T0010AML.T0019AML.T0058LLM03:2025

Global/unverified dependency execution — global npm/yarn package, dotnet tool, or auto-confirmed npx run without version or integrity pinning

95% confidenceline 50

npm i -g

Badge

Markdown

[![Mondoo Skill Check](https://mondoo.com/ai-agent-security/api/badge/github/agentspace-so/runcomfy-agent-skills/nano-banana-2.svg)](https://mondoo.com/ai-agent-security/skills/github/agentspace-so/runcomfy-agent-skills/nano-banana-2)

HTML

<a href="https://mondoo.com/ai-agent-security/skills/github/agentspace-so/runcomfy-agent-skills/nano-banana-2"><img src="https://mondoo.com/ai-agent-security/api/badge/github/agentspace-so/runcomfy-agent-skills/nano-banana-2.svg" alt="Mondoo Skill Check" /></a>

Image URL

https://mondoo.com/ai-agent-security/api/badge/github/agentspace-so/runcomfy-agent-skills/nano-banana-2.svg

Secure your AI agents

Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.

Continuous scanning of skills across all registries
Policy enforcement before skills reach your agents
Integration with your existing security workflow