image-to-video

Name: runcomfy-agent-skills/image-to-video
Author: agentspace-so

Share on X Share on LinkedIn Share on Bluesky

40Medium

The skill executes unpinned, unverified remote packages and performs unrestricted system operations while exposing users to potential adversarial prompt injection through external image processing.

ThreatsCI SM CS BC S HITL

Threat Analysis

AI Agent Traps ↗Scanned 6/30/2026

Content InjectionPerception1 finding

Semantic ManipulationReasoningclean

Cognitive StateMemory & Learning2 findings

Behavioural ControlActionclean

SystemicMulti-Agent Dynamicsclean

Human-in-the-LoopHuman Overseerclean

Skill Info

Nameagentspace-so/runcomfy-agent-skills/image-to-video

Registrygithub

Versionfca19ae084c2

PURLpkg:github/agentspace-so/runcomfy-agent-skills@fca19ae084c2?skill=image-to-video

Stars27

Installs320,300

Source

Repository ↗SKILL.md ↗

Install

This skill has findings worth reviewing before installing.

GitHub

320,300 installs

Skills.shDocs

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

Assessments (3)

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 48

npm i -g

Missing allowed-tools declarationlowunauthorized tool use

Skill executes commands, writes files, or accesses the network but declares no allowed-tools, so its tool surface cannot be reviewed or constrained.

90% confidence

Potential for Indirect Prompt Injection via Image URLslowprompt injectionAML.T0051AML.T0051.000AML.T0051.001AML.T0054LLM01:2025

The skill encourages users to provide external image URLs which are processed by remote model servers. If the model server is susceptible to adversarial image-based prompt injection, the user's intent could be hijacked.

70% confidenceline 203

Treat external URLs as untrusted; image-based prompt injection is a known risk for any image-edit / video-edit model.

Badge

Markdown

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

HTML

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

Image URL

https://mondoo.com/ai-agent-security/api/badge/github/agentspace-so/runcomfy-agent-skills/image-to-video.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