Skills infsh-cli

📦

infsh-cli

Name: infsh-cli
Author: infsh-skills

Content revision r2 Critical 🌐 Network access🔑 Env variables📁 Filesystem access⚙️ External commands

Run Cloud AI Apps from the Command Line

Cloud AI workflows often require different APIs and tools. This skill guides Claude, Codex, and Claude Code through inference.sh CLI 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/infsh-skills-infsh-cli.md and its manifest at https://skillstore.io/api/skills/infsh-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/infsh-skills-infsh-cli.md Signed manifest GET /api/skills/infsh-skills-infsh-cli/manifest Signed lockfile GET /api/skills/infsh-skills-infsh-cli/lockfile

Test it

Using "infsh-cli". Find a fast image model for product concept art.

Expected outcome:

Recommended app: falai/flux-2-klein-lora.
Reason: The catalog describes it as a fast FLUX option.
Next step: Inspect its current input schema before running.

Using "infsh-cli". Prepare a video generation run from my local image.

Expected outcome:

Selected app: falai/wan-2-5-i2v.
Upload approval required for the selected local image path.
The run will begin only after approval and input validation.

Using "infsh-cli". Track a long-running Veo task.

Expected outcome:

The task was submitted without waiting. Its task identifier is ready for status checks and result retrieval.

Security Audit

Critical

v5 • 8/6/2026 Open versioned report

Four pipe-to-shell installation instructions are confirmed critical risks, and the manual installation uses a dynamic remote download URL. Most other alerts are documentation links, placeholders, Markdown syntax, or standard configuration paths. The skill also enables local-file uploads and authenticated external actions that require explicit user control.

Files scanned

608

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

The command sends an unpinned remote response directly to sh. A compromised endpoint could execute arbitrary code without prior inspection.

Critical

references/authentication.md:44

Pipe to shell pattern

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

The reinstall command again executes an unpinned remote response directly in a shell. This creates the same arbitrary-code supply-chain risk.

Critical

references/cli-reference.md:6

Pipe to shell pattern

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

The installation command directly executes remote content through sh. Endpoint or transport compromise would provide arbitrary code execution.

Critical

SKILL.md:18

Pipe to shell pattern

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

The primary installation path executes an unpinned remote response directly through sh. This permits arbitrary code execution if the source is compromised.

High

SKILL.md:58-73 references/running-apps.md:21-42

Automatic Local File Upload

The CLI automatically uploads supplied local paths to inference.sh. An agent could expose any readable file if a path comes from untrusted instructions.

Both files explicitly state that local paths are uploaded and provide absolute, relative, and home-directory examples.

High

SKILL.md:4 SKILL.md:51-52 references/cli-reference.md:63-73

Broad Authenticated External Actions

The allowed belt command scope includes public posts and app deployment. These actions can change external accounts or publish content without a built-in confirmation boundary.

The frontmatter allows every belt subcommand, while the examples document public posting and deployment operations.

Capability review items (2)

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

SKILL.md:7

Ruby/shell backtick execution

> **Install the belt CLI skill:** `npx skills add belt-sh/cli`

The line directs users to run npx and install another remote skill without a pinned version. That creates a real dependency supply-chain risk.

Medium

SKILL.md:28

Shell command substitution

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

The command derives a download URL from a remote manifest using fragile text parsing. Remote content controls the fetched asset location.

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:9 SKILL.md:13 SKILL.md:18 SKILL.md:22 SKILL.md:27 SKILL.md:28 SKILL.md:141 SKILL.md:142 SKILL.md:143 SKILL.md:144 SKILL.md:145 SKILL.md:146 SKILL.md:147

🔑 Env variables (3)

references/authentication.md:30 references/authentication.md:53 references/cli-reference.md:79

📁 Filesystem access (5)

references/cli-reference.md:91 references/cli-reference.md:91 references/running-apps.md:41 SKILL.md:33 SKILL.md:33

⚙️ External commands (22)

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/infsh-skills-infsh-cli/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/infsh-skills-infsh-cli/security.svg)](https://skillstore.io/skills/infsh-skills-infsh-cli?utm_source=security_passport_badge)

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/infsh-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

infsh-skills. (2026). infsh-cli security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/infsh-skills-infsh-cli/audits/5

BibTeX citation

@techreport{infsh-skills-infsh-skills-infsh-cli-2026,
  author = {infsh-skills},
  title = {infsh-cli security audit report (audit version 5)},
  institution = {Skillstore},
  year = {2026},
  number = {5},
  url = {https://skillstore.io/skills/infsh-skills-infsh-cli/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: "infsh-cli security audit report (audit version 5)"
version: "unspecified"
type: report
authors:
  - name: "infsh-skills"
date-released: "2026-08-06"
url: "https://skillstore.io/skills/infsh-skills-infsh-cli/audits/5"
identifiers:
  - type: other
    value: "skillstore:infsh-skills-infsh-cli:audit:5"
    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 41

Updated

2026-08-21

qu-skills

qu-skills-infsh-cli

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 19

Updated

2026-08-21

tool-belt

tool-belt-infsh-cli

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 13

Updated

2026-08-21

skillssh

skillssh-infsh-cli

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 9

Updated

2026-08-21

inference-skills

inference-skills-infsh-cli

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 9

Updated

2026-08-21

inference-sh-skills

inference-sh-skills-infsh-cli

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 8

Updated

2026-08-21

infsh-skills Current

infsh-skills-infsh-cli

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 7

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 Multimodal Features

Find suitable image, video, language, or search apps and test them from a terminal workflow.

Produce Media Assets

Generate images, videos, speech, or 3D assets while tracking long-running cloud tasks.

Operate Cloud AI Jobs

Pin app versions, submit asynchronous runs, save results, and inspect failures in repeatable workflows.

Try These Prompts

Find an App

Search inference.sh for apps that can perform [task]. Compare the most relevant options and do not run anything yet.

Inspect App Requirements

Inspect [app name], summarize its required inputs, and generate a sample input file. Ask before changing any existing file.

Run a Media Task

Run [app name] with [prompt and settings]. If a local file is needed, show its path and request upload approval first.

Build an Asynchronous Workflow

Create a version-pinned workflow for [goal]. Submit without waiting, track the task, save results, and stop on authentication or quota errors.

Best Practices

Inspect each app schema and current version before preparing inputs.
Request explicit approval before uploads, installations, deployments, posts, messages, follows, or other external changes.
Use version pinning and save task identifiers for repeatable asynchronous workflows.

Avoid

Do not send credentials, private files, or unrelated workspace data as app inputs.
Do not execute pipe-to-shell installers or unverified dynamic download commands.
Do not assume model availability, pricing, quotas, or input schemas remain unchanged.