Skills inference-sh

📦

inference-sh

Name: inference-sh
Author: inference-sh

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

Run AI Apps with inference.sh

AI model workflows often require separate APIs, credentials, and task tracking. This skill helps Claude, Codex, and Claude Code use inference.sh CLI 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 "inference-sh" from https://skillstore.io/skills/inference-sh-inference-sh.md and its manifest at https://skillstore.io/api/skills/inference-sh-inference-sh/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-inference-sh.md Signed manifest GET /api/skills/inference-sh-inference-sh/manifest Signed lockfile GET /api/skills/inference-sh-inference-sh/lockfile

Test it

Using "inference-sh". Find a fast image model for a product concept render.

Expected outcome:

The skill would list relevant image apps, compare speed and quality, then recommend a model to run.

Using "inference-sh". Run a long video task and tell me when it is done.

Expected outcome:

The skill would submit the task, record the task ID, check progress, and summarize the final result link.

Using "inference-sh". Prepare a social post but do not publish it yet.

Expected outcome:

The skill would draft the post text and ask for explicit approval before any Twitter/X action.

Security Audit

Critical

v4 • 7/5/2026 Open versioned report

Confirmed critical remote-installer findings where curl output is piped directly into sh. Most API key, shell completion, documentation URL, and Markdown backtick matches are false positives. Semantic review found broad infsh CLI permission and Twitter/X automation risks that need guardrails before publication.

Files scanned

533

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 instruction pipes a remote installer directly into sh without checksum, signature, or pinned version. It could execute arbitrary code during setup.

Critical

references/authentication.md:44

Pipe to shell pattern

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

The reinstall instruction pipes a remote installer directly into sh. This remains a critical supply-chain execution pattern even when used for setup.

Critical

references/cli-reference.md:6

Pipe to shell pattern

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

The CLI installation command downloads a script and pipes it directly to sh. This is a critical remote code execution supply-chain pattern.

Critical

SKILL.md:19

Pipe to shell pattern

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

The skill presents a remote installer piped directly into sh. This is a critical setup pattern because a changed or compromised installer can execute arbitrary code.

High

SKILL.md:9 references/cli-reference.md:59-65

Broad CLI Permission Scope

The skill grants Bash(infsh *), which permits any inference.sh CLI subcommand. The CLI reference includes deployment and source pull commands, so agent actions can exceed simple app runs.

The allowed-tools line is explicit, and the CLI reference documents deploy and pull subcommands. The risk depends on agent behavior, but permission scope is broad.

High

SKILL.md:38-39 SKILL.md:67

Social Media Automation Actions

The skill examples include posting to Twitter/X and list DM, follow, like, and retweet actions. These actions can create account activity without careful confirmation.

The cited lines directly show social media posting and account interaction capabilities. The finding is about user-account impact, not command syntax.

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

references/authentication.md:6

Hardcoded URL

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

The URL is part of a command that downloads an installer and immediately executes it with sh. That creates remote supply-chain risk if the endpoint or transport is compromised.

Medium

references/authentication.md:44

Hardcoded URL

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

The URL is part of a reinstall command that downloads an installer and immediately executes it with sh. This is risky without pinning, checksums, or signature verification.

Medium

references/cli-reference.md:6

Hardcoded URL

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

The URL is used in a command that fetches a remote installer for immediate shell execution. The network dependency is part of a risky install path.

Medium

SKILL.md:19

Hardcoded URL

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

The URL is used in a command that fetches and executes a remote installer. That network dependency is risky without verification or version pinning.

Risk Factors

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

HTML badge

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

Embed card

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

BibTeX citation

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

Generate Media Assets

Create image, video, audio, or 3D outputs from cloud AI apps without managing local GPUs.

Prototype Model Workflows

Find models, inspect schemas, create sample inputs, and run tasks from one CLI workflow.

Run Research Tasks

Use search and LLM apps to gather information, summarize findings, and track long-running jobs.

Try These Prompts

Find Apps by Category

Use inference.sh to list image generation apps. Show the best options and explain what each app is for.

Prepare a Sample Run

Create a safe sample input for a FLUX image app, explain each field, and ask before running it.

Track a Long Task

Run a video generation task without waiting, capture the task ID, and check status until the result is ready.

Plan a Multi-App Workflow

Design a workflow that searches for references, generates a script, creates a video, and saves final outputs for review.

Best Practices

Review every command before execution, especially install, deploy, and social media commands.
Use scoped API keys and store them in a secret manager.
Pin app versions when reproducibility matters.