video-edit

Name: runcomfy-agent-skills/video-edit
Author: agentspace-so

Share on X Share on LinkedIn Share on Bluesky

40Medium

The skill lacks defined tool constraints, executes unpinned and unverified dependencies, and processes external media, creating significant risks for arbitrary code execution and indirect prompt injection attacks.

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/video-edit

Registrygithub

Versionfca19ae084c2

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

Stars27

Installs321,200

Source

Repository ↗SKILL.md ↗

Install

This skill has findings worth reviewing before installing.

GitHub

321,200 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 49

npm i -g

Potential for Indirect Prompt Injection via URL inputslowindirect prompt injection

The skill accepts external video and image URLs which are processed by remote models; if these models are susceptible to adversarial inputs, they could be used to perform indirect prompt injection against the user's workflow.

80% confidence

The skill documentation acknowledges: 'image-based prompt injection is a known risk for any image-edit / video-edit model.'

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

Badge

Markdown

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

HTML

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

Image URL

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