Skills ai-content-pipeline

📦

ai-content-pipeline

Name: ai-content-pipeline
Author: inference-sh

Content revision r1 Critical ⚙️ External commands🌐 Network access

Build AI Content Pipelines

Multi-step media production often requires many tools and repeated handoffs. This skill maps text, image, video, and audio steps into repeatable inference.sh workflows.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

Do not auto-install this skill.

The canonical policy requires operator review before any installation action.

Install with my Agent

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

Agent request

Review the Skillstore skill "ai-content-pipeline" from https://skillstore.io/skills/inference-sh-ai-content-pipeline.md and its manifest at https://skillstore.io/api/skills/inference-sh-ai-content-pipeline/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.

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/inference-sh-ai-content-pipeline.md Signed manifest GET /api/skills/inference-sh-ai-content-pipeline/manifest Signed lockfile GET /api/skills/inference-sh-ai-content-pipeline/lockfile

Test it

Using "ai-content-pipeline". A creator asks for a 30-second video pipeline about a new productivity habit.

Expected outcome:

The skill returns a staged plan covering script, voiceover, background image, image animation, captions, media merge, and review checkpoints.

Using "ai-content-pipeline". A marketer needs a product showcase for wireless earbuds.

Expected outcome:

The skill outlines product image generation, reveal animation, optional upscaling, music selection, audio volume, and final assembly checks.

Using "ai-content-pipeline". A team wants to turn a blog post into a video series.

Expected outcome:

The skill proposes summarization, point-by-point visuals, clip animation, narration, transitions, and storage of intermediate outputs.

Security Audit

Critical

v4 • 7/6/2026 Open versioned report

Most static external-command findings are false positives caused by Markdown code fences or inline app names. The real issue is the Quick Start command that downloads a remote installer and pipes it directly to sh without integrity verification.

Files scanned

256

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

Critical

SKILL.md:21

Pipe to shell pattern

curl -fsSL https://cli.inference.sh | sh && infsh login

Line 21 downloads a remote installer and pipes it directly to sh. A compromised endpoint or network path could execute arbitrary code without checksum or signature verification.

Capability review items (1)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

High

SKILL.md:21

Hardcoded URL

curl -fsSL https://cli.inference.sh | sh && infsh login

The hardcoded installer URL is used in a command that immediately executes downloaded content. The network access is security-relevant because it controls code run by the shell.

Detected Patterns

Pipe to shell pattern

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/inference-sh-ai-content-pipeline/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/inference-sh-ai-content-pipeline/security.svg)](https://skillstore.io/skills/inference-sh-ai-content-pipeline?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/inference-sh-ai-content-pipeline?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inference-sh-ai-content-pipeline/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/inference-sh-ai-content-pipeline.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

inference-sh. (2026). ai-content-pipeline security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-sh-ai-content-pipeline/audits/4

BibTeX citation

@techreport{inference-sh-inference-sh-ai-content-pipeline-2026,
  author = {inference-sh},
  title = {ai-content-pipeline security audit report (audit version 4)},
  institution = {Skillstore},
  year = {2026},
  number = {4},
  url = {https://skillstore.io/skills/inference-sh-ai-content-pipeline/audits/4},
  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: "ai-content-pipeline security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
  - name: "inference-sh"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/inference-sh-ai-content-pipeline/audits/4"
identifiers:
  - type: other
    value: "skillstore:inference-sh-ai-content-pipeline:audit:4"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Create Short Social Videos

Turn a topic into a short video plan with script, voiceover, visuals, animation, captions, and final media assembly.

Produce Product Demos

Plan a product showcase with generated product imagery, reveal animation, optional upscaling, background music, and final merge steps.

Convert Blogs To Video

Standardize a repeatable flow for summarizing articles, creating visuals, animating clips, adding narration, and preserving intermediate assets.

Try These Prompts

Plan A Simple Pipeline

Plan a beginner image-to-video pipeline for a 30-second social post about [topic]. Include each stage, expected output, and quality checks.

Create A Short Video Workflow

Create a YouTube Short workflow for [topic]. Include script generation, voiceover, background visual, animation, captions, and final merge steps.

Adapt A Product Demo

Adapt the product demo workflow for [product]. Include visual prompt direction, voice style, music needs, upscaling, and final review checks.

Design A Production Pipeline

Design a reusable content production pipeline for [team]. Include model choices, naming conventions, review gates, privacy checks, and failure handling.

Best Practices

Plan each stage before running commands and name expected inputs and outputs.
Save intermediate media and metadata so every step can be reviewed or repeated.
Test one pipeline step at a time before merging final media.

Avoid

Do not paste private source material into hosted models without approval.
Do not run installer commands from remote URLs without verification.
Do not chain every step before validating quality, timing, and aspect ratios.

Frequently Asked Questions

Does this skill create media by itself?

No. It provides workflow guidance and command examples for inference.sh apps that perform media generation and processing.

Which workflow steps does it cover?

It covers scripts, research, image generation, video generation, text-to-speech, music, foley, upscaling, merging, and captions.

Do I need an inference.sh account?

Yes. The examples require the inference.sh CLI and authentication before app runs can complete.

Can I use private content?

Use private material only when your organization allows sending it to hosted model services.

Can it automate a full production workflow?

It can outline and sequence steps, but it does not provide a scheduler, retry system, or asset database.

Is it suitable for Claude, Codex, and Claude Code?

Yes. The skill declares support for Claude, Codex, and Claude Code workflows.

Developer Details

Author

inference-sh

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/inference-sh/skills/tree/main/skills/ai-content-pipeline/

Ref

a06681402992ceae98ba04d54cfd4ab004862696

Maintenance freshness

7/18/2026

Usage

6 downloads · 166 views

File structure

📄 SKILL.md

ai-content-pipeline

Install with my Agent

Agent-readable resources

Test it

Security Audit

Confirmed security concerns (1)

Risk Factors

Detected Patterns

Copy report link

Markdown badge

HTML badge

Embed card

APA citation

BibTeX citation

CITATION.cff

Skillstore Score

What You Can Build

Create Short Social Videos

Produce Product Demos

Convert Blogs To Video

Try These Prompts

Best Practices

Avoid

Frequently Asked Questions

Developer Details