Skills controlnet-pose

📦

controlnet-pose

Name: controlnet-pose
Author: agentspace-so

Content revision r2 High Risk ⚙️ External commands🌐 Network access📁 Filesystem access

Generate Pose-Controlled Images and Videos

Pose and motion references are difficult to route across image and video generation models. This skill selects a suitable RunComfy model and prepares the generation request.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

Stop for confirmation before installing.

Review the plan and obtain explicit user consent before changing files.

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "controlnet-pose" from https://skillstore.io/skills/agentspace-so-controlnet-pose.md and its manifest at https://skillstore.io/api/skills/agentspace-so-controlnet-pose/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/agentspace-so-controlnet-pose.md Signed manifest GET /api/skills/agentspace-so-controlnet-pose/manifest Signed lockfile GET /api/skills/agentspace-so-controlnet-pose/lockfile

Test it

Using "controlnet-pose". Use this dance video to animate my illustrated character.

Expected outcome:

Selected Kling Motion Control Pro for video motion transfer. Requested the reference video and character image URLs before generation.

Using "controlnet-pose". Create a samurai image in this OpenPose stance.

Expected outcome:

Selected Z-Image Turbo ControlNet LoRA for still-image pose conditioning. Prepared the control image, prompt, and output location.

Using "controlnet-pose". Use pose and depth controls together for a product scene.

Expected outcome:

Identified a multi-condition request and recommended a hosted ComfyUI workflow instead of a single-condition CLI endpoint.

Security Audit

High Risk

v5 • 7/23/2026 Open versioned report

The static analyzer mostly mistook Markdown syntax, documentation links, and placeholder URLs for executable behavior. Two contextual risks remain: unpinned package execution and shell examples that can become injectable when an agent substitutes unescaped user input.

Files scanned

187

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (2)

High

SKILL.md:85-91 SKILL.md:109-115 SKILL.md:172-175

Unsafe Shell Quoting for User-Controlled Inputs

Examples place JSON inside single-quoted shell arguments while prompts and URLs can come from users. An apostrophe can end the quote and enable command injection.

The examples visibly use single-quoted JSON, and the skill expects an agent to insert user prompts or URLs. Runtime escaping behavior is not specified.

Medium

SKILL.md:31-36 SKILL.md:170

Unpinned Package Installation and Execution

The installation guidance runs the latest @runcomfy/cli package, including automatic npx installation. Version drift or package compromise would execute new code with user privileges.

Both installation examples omit a version, and npx uses the automatic approval flag. This creates a clear dependency supply-chain exposure.

Risk Factors

⚙️ External commands (33)

🌐 Network access (23)

📁 Filesystem access (2)

SKILL.md:171 SKILL.md:171

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/agentspace-so-controlnet-pose/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/agentspace-so-controlnet-pose/security.svg)](https://skillstore.io/skills/agentspace-so-controlnet-pose?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/agentspace-so-controlnet-pose?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/agentspace-so-controlnet-pose/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/agentspace-so-controlnet-pose.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

agentspace-so. (2026). controlnet-pose security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/agentspace-so-controlnet-pose/audits/5

BibTeX citation

@techreport{agentspace-so-agentspace-so-controlnet-pose-2026,
  author = {agentspace-so},
  title = {controlnet-pose security audit report (audit version 5)},
  institution = {Skillstore},
  year = {2026},
  number = {5},
  url = {https://skillstore.io/skills/agentspace-so-controlnet-pose/audits/5},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "controlnet-pose security audit report (audit version 5)"
version: "unspecified"
type: report
authors:
  - name: "agentspace-so"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/agentspace-so-controlnet-pose/audits/5"
identifiers:
  - type: other
    value: "skillstore:agentspace-so-controlnet-pose:audit:5"
    description: "Skillstore immutable audit report identifier"

Compare variants

3 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Recently maintained

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

runcomfy-com Recommended

runcomfy-com-controlnet-pose

Skillstore Score 79

Evidence Confidence High

Skillstore usage 13

Updated

2026-08-21

doany-ai

doany-ai-controlnet-pose

Skillstore Score 79

Evidence Confidence High

Skillstore usage 13

Updated

2026-08-21

agentspace-so Current

agentspace-so-controlnet-pose

Skillstore Score 38

Evidence Confidence High

Skillstore usage 7

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Transfer Performance Motion

Apply a reference performance video to a target character with Kling Motion Control.

Lock an Image Pose

Generate a new image from an OpenPose, DWPose, depth, or canny control image.

Prototype Character Animation

Route stylized animation drafts to Wan or lower-cost Kling models before final rendering.

Try These Prompts

Create a Pose-Controlled Image

Create an image of [subject] in [setting] using this [OpenPose or DWPose] control image: [URL]. Save the result in [folder].

Transfer Motion to a Character

Transfer the motion from [reference video URL] to [character image URL]. Use [Pro or Standard] quality and save the generated video in [folder].

Choose a Model for a Draft

Compare suitable RunComfy routes for [project]. The input is [media type], the style is [style], and the control reference is [type and URL].

Plan a Multi-Condition Workflow

Plan a workflow using [pose], [depth], and [reference image] controls for [goal]. Identify whether CLI routes suffice or a ComfyUI workflow is required.

Best Practices

Use clean, well-framed references with one clear subject and continuous motion.
Confirm the control type matches the selected model or LoRA.
Review service privacy requirements before sending prompts or media URLs.

Avoid

Do not use still-image routes for video motion transfer.
Do not send multi-condition stacks to a single-condition CLI endpoint.
Do not interpolate untrusted text directly into a shell command.

Frequently Asked Questions

What inputs does video motion transfer require?

It requires a reference performance video URL and a target character image URL.

Which controls work for still images?

The documented route supports pose skeletons, DWPose, canny edges, and depth maps when the selected LoRA matches.

Can it combine pose, depth, and reference controls?

Not through the documented direct endpoint. Use a dedicated hosted ComfyUI workflow for multi-condition stacks.

Does it generate control images?

No. Create pose skeletons or other control images with a separate preprocessor before using this skill.

Where are generated files stored?

The RunComfy CLI downloads results to the output directory selected for the request.

Does it require authentication?

Yes. Sign in with the RunComfy CLI or provide the documented token environment variable in automated environments.

Developer Details

Author

agentspace-so

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/agentspace-so/runcomfy-agent-skills/tree/main/controlnet-pose/

Ref

181fdefcafd96b041926e61c4b2e306ca7e7820e

Maintenance freshness

7/24/2026

Usage

4 downloads · 49 views

File structure

📄 SKILL.md