π¦
routemux-setup
78Connect Your Tools to RouteMux
AI client setup often fails because tools expect different base URL and protocol formats. This skill selects the correct RouteMux endpoint and verifies access.
DevOps & Infrastructure View
Skills routemux-video
π¦
routemux-video
Content revision r1 High Risk βοΈ External commandsπ Network accessπ Env variables
Generate Videos with RouteMux
Video generation APIs require model selection, asynchronous polling, and careful download handling. This skill guides RouteMux submissions and returns completed video files with status details.
Supports: Claude Codex Code(CC)
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 "routemux-video" from https://skillstore.io/skills/rootfily-ai-routemux-video.md and its manifest at https://skillstore.io/api/skills/rootfily-ai-routemux-video/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.
Test it
Using "routemux-video". Generate a five-second clip of rain crossing a neon storefront.
Expected outcome:
The video completed in four minutes. The MP4 is available at /workspace/videos/neon-rain.mp4.
Using "routemux-video". Check which current video model supports my requested format.
Expected outcome:
- Available models were checked from the live RouteMux catalogue.
- The selected model matches the documented video output requirement.
- Approval is required before the billable submission.
Using "routemux-video". Explain why my submitted video did not complete.
Expected outcome:
Job rmx-example failed with the provider message shown. It was not resubmitted, preventing another charge.
Security Audit
High Riskv1 β’ 9/15/2026 Open versioned report
Four findings confirm intentional curl execution for the RouteMux workflow. Other static alerts are harmless Markdown, expected provider URLs, or protected credential use. The submission template permits shell injection if user prompts are inserted without robust escaping.
1
Files scanned
74
Lines analyzed
4
Review items
0
False positives ignored
Confirmed security concerns (1)
High
Unsafe Shell Interpolation in Submission Template
The template places prompt data inside a single-quoted shell argument. Literal substitution can permit command injection when a prompt contains a quote and shell syntax.
The prompt placeholder is inside shell-quoted JSON without structured serialization or escaping guidance. Exploitation depends on how the agent substitutes user text.
Capability review items (4)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Medium
Ruby/shell backtick execution
```bash
The fenced block directs the agent to execute curl for the RouteMux model catalogue.
Medium
Ruby/shell backtick execution
```bash
The fenced block directs the agent to execute curl and submit a billable video job.
Medium
Ruby/shell backtick execution
```bash
The fenced block directs the agent to execute curl while polling a RouteMux job.
Medium
Ruby/shell backtick execution
```bash
The fenced block directs the agent to execute curl and write downloaded video content to disk.
Risk Factors
βοΈ External commands (15)
π Network access (6)
π Env variables (8)
Audited by: codex
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.
Copy report link
https://skillstore.io/skills/rootfily-ai-routemux-video/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/rootfily-ai-routemux-video?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/rootfily-ai-routemux-video?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/rootfily-ai-routemux-video/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/rootfily-ai-routemux-video.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 Β· BibTeX Β· CFF)
APA citation
rootfily-ai. (2026). routemux-video security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/rootfily-ai-routemux-video/audits/1BibTeX citation
@techreport{rootfily-ai-rootfily-ai-routemux-video-2026,
author = {rootfily-ai},
title = {routemux-video security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/rootfily-ai-routemux-video/audits/1},
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: "routemux-video security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "rootfily-ai"
date-released: "2026-09-15"
url: "https://skillstore.io/skills/rootfily-ai-routemux-video/audits/1"
identifiers:
- type: other
value: "skillstore:rootfily-ai-routemux-video:audit:1"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: Medium 55
Architecture
85
Maintainability
87
Content
65
Community
83
Spec Compliance
What You Can Build
Create Short Concept Clips
Generate a short visual concept from a written scene and receive the downloaded MP4 path.
Prototype Product Motion
Test an approved product animation prompt with a current video model before production.
Validate Video API Workflows
Submit one job, monitor asynchronous status, and inspect completion or provider errors.
Try These Prompts
Generate a Basic Clip
Create a five-second video of [subject] in [setting]. Use a suitable RouteMux model and save the completed MP4 in [folder].
Animate a Source Image
Create an image-to-video clip from [image path]. Add [motion], choose a suitable live model, and save the result in [folder].
Compare Models Before Submission
List current video models supporting [requirement]. Compare documented capabilities, then ask me to approve one before submitting a job.
Manage Multiple Approved Clips
Generate [clip count] approved clips from these prompts: [prompts]. Submit sequentially, poll with backoff, report each status, and never retry failed jobs.
Best Practices
- Confirm the selected model before any unrequested billable submission.
- Poll no faster than every ten seconds and increase the interval toward thirty seconds.
- Keep the API key only in ROUTEMUX_API_KEY and exclude it from files, logs, and replies.
Avoid
- Do not choose a model from memory when the live catalogue is available.
- Do not submit multiple alternatives without explicit approval.
- Do not automatically retry failed jobs because each submission can create another charge.
Frequently Asked Questions
What credential does this skill require?
It requires a RouteMux API key stored in the ROUTEMUX_API_KEY environment variable.
How long does video generation take?
Generation usually takes minutes, and timing depends on the selected model and provider load.
How does the skill choose a model?
It queries the live RouteMux catalogue and selects a video-capable model matching the request.
Will failed jobs retry automatically?
No. The skill reports the failure and avoids automatic retries because each submission may incur a charge.
Where is the completed video saved?
The skill downloads completed content to an absolute MP4 path and reports that path.
Can it create image-to-video clips?
The skill advertises image-to-video use, but its workflow does not document the required source image parameters.
Developer Details
Author
rootfily-aiLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
f6aa6f4e154bf3a8f90ac2069cbe691b8c5a5980
Maintenance freshness
9/15/2026
Usage
0 downloads Β· 0 views
File structure
π SKILL.md
More from rootfily-ai
View allπ¦
routemux-models
78Check RouteMux Models and Capabilities
Choosing a model without current availability, pricing, or capability data can cause failed requests and poor tradeoffs. This skill queries the live RouteMux catalogue for the models your key can call.
Research & Learning View
π¦
routemux-images
38Generate and Edit Images with RouteMux
Coding agents can lose built-in image tools when routed through a custom API gateway. This skill uses RouteMux endpoints to generate or edit images.
Design & Creative View
Related Skills
View allπ¦
ai-video-generation
78Generate AI Videos with RunComfy
by runcomfy-com
Choosing the right video model and prompt format can slow production work. This skill selects a RunComfy route and prepares clear CLI-ready generation guidance.
Design & Creative View
π¦
p-video
78Generate Pruna Videos from Text and Images
by inferen-sh
Creating video model commands requires choosing compatible inputs and settings. This skill guides Pruna P-Video and WAN generation through the inference.sh CLI.
Design & Creative View
π¦
wan-2-7
78Generate Wan 2.7 Videos on RunComfy
by runcomfy-com
Teams need repeatable text-to-video prompts without guessing every RunComfy option. This skill gives Claude, Codex, and Claude Code a focused Wan 2.7 workflow for prompts, audio URLs, durations, aspect ratios, and outputs.
Design & Creative View
π¦
fal-generate
77Generate Media with fal.ai Models
by sickn33
AI media creation needs clear model guidance and well-scoped prompts. This skill helps Claude, Codex, and Claude Code plan fal.ai image and video generation tasks.
Design & Creative View
π¦
seedance-2-5-image-to-video
77Animate Still Images with Seedance 2.5
by genmedia-labs
Static images cannot show motion, camera movement, or synchronized sound. This skill creates directed 720p clips from one image through Seedance 2.5.
Design & Creative View
π¦
magic-hour-image-to-video
76Animate Images into Short Videos with Magic Hour
by magichourhq
A single still image is rarely enough to produce a convincing short video, because appearance problems cannot be fixed by motion. This skill solves appearance in the start frame first, then animates the approved frame with Magic Hour and inspects the finished clip before delivery.
Design & Creative View