Background Removal

Name: skills/background-removal
Author: tool-belt

Share on X Share on LinkedIn Share on Bluesky

100Critical

The skill encourages `npx skills add`, enabling arbitrary code execution from npm, posing a significant supply chain risk.

ThreatsCI SM CS BC S HITL

Behavior Analysis

Description verified — behavior matches claim

Claims to do

Background Removal: Remove backgrounds from images via [inference.sh](https://inference.sh) CLI.

Actually does

This skill executes `infsh` CLI commands to interact with the `inference.sh` platform. It runs `infsh/birefnet` and `falai/reve` to remove or change image backgrounds, and `falai/flux-dev-lora` to generate images, taking image URLs as input. It also uses `npx skills` to add other skills and `infsh app list` to browse applications.

Threat Analysis

AI Agent Traps ↗Scanned 4/15/2026

Content InjectionPerceptionclean

Semantic ManipulationReasoningclean

Cognitive StateMemory & Learningclean

Behavioural ControlAction1 finding

SystemicMulti-Agent Dynamicsclean

Human-in-the-LoopHuman Overseerclean

Skill Info

Nametool-belt/skills/background-removal

Registrygithub

Versionb684df19dfd3

PURLpkg:github/tool-belt/skills@b684df19dfd3?skill=background-removal

Stars414

Source

Repository ↗SKILL.md ↗

SHA-25691ce0cf8d80a...

SHA-1c13f600ff642...

MD55e673edbcd14...

TLSH2d5185b3d5cb...

Size2,617 bytes

Install

This skill has been flagged as potentially malicious. Review the findings below before installing.

GitHub

https://github.com/tool-belt/skills/tree/main/skills/background-removal

Claude CodeDocs

/plugin marketplace add tool-belt/skills

/plugin install background-removal@tool-belt/skills

Skills.shDocs

npx skills add https://github.com/tool-belt/skills

Assessments (1)

AI Agent Traps ↗

Arbitrary Code Execution via npx (Supply Chain Risk)criticalsupply chain

The skill demonstrates and encourages the use of 'npx skills add', which can download and execute arbitrary code from the npm registry. This introduces a significant supply chain risk, allowing for arbitrary command execution if a malicious package is installed.

100% confidenceline 73

npx skills add inference-sh/skills@infsh-cli

Badge

Markdown

[![Mondoo Skill Check](https://mondoo.com/ai-agent-security/api/badge/github/tool-belt/skills/background-removal.svg)](https://mondoo.com/ai-agent-security/skills/github/tool-belt/skills/background-removal)

HTML

<a href="https://mondoo.com/ai-agent-security/skills/github/tool-belt/skills/background-removal"><img src="https://mondoo.com/ai-agent-security/api/badge/github/tool-belt/skills/background-removal.svg" alt="Mondoo Skill Check" /></a>

Image URL

https://mondoo.com/ai-agent-security/api/badge/github/tool-belt/skills/background-removal.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