Skills infsh-cli

📦

infsh-cli

Name: infsh-cli
Author: inference-sh-skills

Content revision r1 Critical 🌐 Network access🔑 Env variables📁 Filesystem access⚙️ External commands

Run inference.sh AI Apps from the CLI

Teams need a consistent way to run hosted AI apps without managing GPUs. This skill guides Claude, Codex, and Claude Code through CLI setup, app discovery, execution, and task tracking.

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 "infsh-cli" from https://skillstore.io/skills/inference-sh-skills-infsh-cli.md and its manifest at https://skillstore.io/api/skills/inference-sh-skills-infsh-cli/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-skills-infsh-cli.md Signed manifest GET /api/skills/inference-sh-skills-infsh-cli/manifest Signed lockfile GET /api/skills/inference-sh-skills-infsh-cli/lockfile

Test it

Using "infsh-cli". Find an image model for a quick product mockup.

Expected outcome:

Suggested FLUX and SDXL options, explained speed and quality tradeoffs, and stopped before running a paid task.

Using "infsh-cli". Run a video generation job and check it later.

Expected outcome:

Prepared a sample input, submitted the task after approval, returned the task ID, and described how to fetch the final result.

Using "infsh-cli". Use a local image for upscaling.

Expected outcome:

Confirmed the file path, warned that the image would upload to inference.sh, then ran the selected upscaler after approval.

Security Audit

Critical

v4 • 7/5/2026 Open versioned report

The skill is legitimate documentation for the inference.sh CLI, but it includes remote installer commands that pipe downloaded content to a shell and a dynamic download command substitution. Most Markdown backtick, API-key placeholder, hidden-path, and documentation-link findings are false positives. Additional contextual risk comes from automatic local file uploads and Twitter/X account automation.

Files scanned

596

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (6)

Critical

references/authentication.md:6

Pipe to shell pattern

curl -fsSL https://cli.inference.sh | sh

This command downloads a remote installer and executes it immediately with sh. Users cannot review the script before execution in this flow.

Critical

references/authentication.md:44

Pipe to shell pattern

curl -fsSL https://cli.inference.sh | sh

The reinstall path repeats the remote pipe-to-shell pattern. This can execute changed remote code with the user privileges of the shell.

Critical

references/cli-reference.md:6

Pipe to shell pattern

curl -fsSL https://cli.inference.sh | sh

This installation command executes a remote script through sh. The content is not available for review in the skill before execution.

Critical

SKILL.md:16

Pipe to shell pattern

curl -fsSL https://cli.inference.sh | sh

The main installation command pipes a remote script directly into sh. This is a critical supply-chain execution pattern for a community skill.

High

SKILL.md:56-72 references/running-apps.md:21-37

Automatic Local File Uploads to External Service

The skill states that local file paths are automatically uploaded when app inputs accept files. This can expose private images, audio, screenshots, or other media if run without explicit approval.

Both cited sections directly describe automatic uploads and provide commands using local image, audio, and media paths.

High

SKILL.md:49-50 SKILL.md:96 SKILL.md:117-118

State-Changing Twitter/X Automation

The skill includes examples and category listings for posting tweets, posting media, sending DMs, following users, liking posts, and retweeting. These actions can mutate a connected social account and should require explicit confirmation.

The cited lines name concrete Twitter/X write actions and include command examples for posting. This is clear state-changing account automation.

Capability review items (12)

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:26

Shell command substitution

> curl -LO $(curl -fsSL https://dist.inference.sh/cli/manifest.json | grep -o '"url":"[^"]*"' | grep

The command substitution fetches a remote manifest and derives the binary URL inside the shell command. This makes the downloaded artifact dynamic and harder to review.

High

SKILL.md:23-32

Template literal with command substitution

> ```bash

The matched install block contains dynamic command substitution and moves the resulting binary into the user path. The pattern is risky even though it appears in documentation.

Medium

SKILL.md:15-18

Ruby/shell backtick execution

```bash

The matched Markdown block contains a remote installer command followed by login. Although the pattern name is imprecise, the shell snippet is executable setup guidance.

Medium

SKILL.md:23-32

Ruby/shell backtick execution

> ```bash

The manual install block downloads files, extracts an archive, and moves a binary into the user path. This is executable installation guidance from remote artifacts.

Medium

SKILL.md:36-54

Ruby/shell backtick execution

```bash

The examples run hosted apps through the belt CLI, including a Twitter posting app. These are intentional commands but can send data or perform account actions.

Medium

SKILL.md:60-72

Ruby/shell backtick execution

```bash

The block runs belt commands that upload local media paths and can post media to Twitter/X. That creates data-sharing and account-action risk if run without approval.

Medium

SKILL.md:101-127

Ruby/shell backtick execution

```bash

The related-skills block uses npx skills add commands that can install additional skill packages. This creates a dependency and supply-chain risk if executed automatically.

Low

references/authentication.md:6

Hardcoded URL

curl -fsSL https://cli.inference.sh | sh

The URL is used in a curl pipe-to-shell installation command. It fetches executable installer content from the network before local review.

Low

references/authentication.md:44

Hardcoded URL

curl -fsSL https://cli.inference.sh | sh

The URL is used in a reinstall command that pipes remote content to a shell. This is a supply-chain risk if the endpoint or transport is compromised.

Low

references/cli-reference.md:6

Hardcoded URL

curl -fsSL https://cli.inference.sh | sh

The URL appears inside a curl pipe-to-shell installer command. Network-fetched executable installer content creates a supply-chain risk.

Low

SKILL.md:16

Hardcoded URL

curl -fsSL https://cli.inference.sh | sh

The URL is used in a curl pipe-to-shell installer command. That fetches executable installer content from a remote endpoint.

Low

SKILL.md:26

Hardcoded URL

> curl -LO $(curl -fsSL https://dist.inference.sh/cli/manifest.json | grep -o '"url":"[^"]*"' | grep

The URL is used inside a dynamic download command for the CLI manifest. It participates in selecting a remote binary for local installation.

Risk Factors

🌐 Network access (17)

references/authentication.md:6 references/authentication.md:44 references/cli-reference.md:6 references/running-apps.md:152 SKILL.md:7 SKILL.md:11 SKILL.md:16 SKILL.md:20 SKILL.md:25 SKILL.md:26 SKILL.md:138 SKILL.md:139 SKILL.md:140 SKILL.md:141 SKILL.md:142 SKILL.md:143 SKILL.md:144

🔑 Env variables (3)

references/authentication.md:30 references/authentication.md:53 references/cli-reference.md:72

📁 Filesystem access (5)

references/cli-reference.md:84 references/cli-reference.md:84 references/running-apps.md:41 SKILL.md:31 SKILL.md:31

⚙️ External commands (20)

Detected Patterns

Pipe to shell pattern×4

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-skills-infsh-cli/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-skills-infsh-cli/security.svg)](https://skillstore.io/skills/inference-sh-skills-infsh-cli?utm_source=security_passport_badge)

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/inference-sh-skills-infsh-cli.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-skills. (2026). infsh-cli security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-sh-skills-infsh-cli/audits/4

BibTeX citation

@techreport{inference-sh-skills-inference-sh-skills-infsh-cli-2026,
  author = {inference-sh-skills},
  title = {infsh-cli security audit report (audit version 4)},
  institution = {Skillstore},
  year = {2026},
  number = {4},
  url = {https://skillstore.io/skills/inference-sh-skills-infsh-cli/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: "infsh-cli security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
  - name: "inference-sh-skills"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/inference-sh-skills-infsh-cli/audits/4"
identifiers:
  - type: other
    value: "skillstore:inference-sh-skills-infsh-cli:audit:4"
    description: "Skillstore immutable audit report identifier"

Compare variants

9 installable variants

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

Why this variant is first

Higher Skillstore usage

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

inferen-sh Recommended

inferen-sh-infsh-cli

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 40

Updated

2026-08-21

qu-skills

qu-skills-infsh-cli

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 18

Updated

2026-08-21

tool-belt

tool-belt-infsh-cli

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 12

Updated

2026-08-21

skillssh

skillssh-infsh-cli

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 8

Updated

2026-08-21

inference-skills

inference-skills-infsh-cli

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 8

Updated

2026-08-21

inference-sh-skills Current

inference-sh-skills-infsh-cli

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 7

Updated

2026-08-21

infsh-skills

infsh-skills-infsh-cli

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 6

Updated

2026-08-21

101-skills

101-skills-infsh-cli

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 5

Updated

2026-08-21

halt-catch-fire

halt-catch-fire-infsh-cli

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 3

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Prototype Hosted AI Features

Find and run image, video, text, or search apps before adding model calls to a product workflow.

Generate Media Assets

Run image, video, audio, upscaling, and 3D apps from a repeatable command workflow.

Automate Cloud Inference Tasks

Create samples, submit long jobs, check task status, and save outputs for operations scripts.

Try These Prompts

Find a Starter App

Use infsh-cli to find inference.sh apps for [task]. List safe options, explain the categories, and do not run anything yet.

Run a Basic Generation

Use infsh-cli to run [app name] with this prompt: [prompt]. Show the command first and wait for my approval.

Process Local Media

Use infsh-cli with [local file path] for [target app]. Confirm the exact file path and upload destination before running.

Build a Multi-Step Workflow

Plan an inference.sh workflow that discovers apps, creates sample input, runs the selected app, tracks the task, and saves the result.

Best Practices

Inspect remote installer commands and checksums before installing the CLI.
Get explicit approval before uploading local files or running paid model jobs.
Keep API keys in environment or secret storage, not in shared prompts or logs.

Avoid

Pipe a remote installer into a shell without inspecting or pinning it.
Upload private local files by path without confirming the exact file.
Use Twitter/X automation without approving the account, action, and final text.

Frequently Asked Questions

Does this skill install inference.sh automatically?

It provides installation guidance, but users should inspect installer commands and approve execution before the CLI is installed.

Does it require an API key?

Authenticated use requires browser login or INFSH_API_KEY for scripts and CI.

Can it access local files?

It can guide commands that upload local file paths when an app accepts media inputs. Confirm paths before running.

Can it post to Twitter/X?

The referenced apps include Twitter/X posting and engagement actions. Require explicit approval before any account-changing command.

Does it run models locally?

No. The CLI runs hosted apps through inference.sh, so prompts and files may leave the local machine.

Which AI tools can use it?

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

Developer Details

Author

inference-sh-skills

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/inference-sh-skills/skills/tree/main/tools/infsh-cli/

Ref

a25199bc7d6b82598536822d1738eb5d5f54025b

Maintenance freshness

7/21/2026

Usage

3 downloads · 109 views

File structure

📁 references/

📄 app-discovery.md

📄 authentication.md

📄 cli-reference.md

📄 running-apps.md

📄 SKILL.md