Skills javascript-sdk

📦

javascript-sdk

Name: javascript-sdk
Author: inferen-sh

Content revision r2 High Risk ⚙️ External commands📁 Filesystem access🔑 Env variables🌐 Network access⚡ Contains scripts

Build Apps with the inference.sh JavaScript SDK

JavaScript teams need clear patterns for adding hosted AI tasks and agents. This skill provides SDK guidance for execution, streaming, files, tools, sessions, and proxies.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

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 "javascript-sdk" from https://skillstore.io/skills/inferen-sh-javascript-sdk.md and its manifest at https://skillstore.io/api/skills/inferen-sh-javascript-sdk/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.

Markdown detail GET /skills/inferen-sh-javascript-sdk.md Signed manifest GET /api/skills/inferen-sh-javascript-sdk/manifest Signed lockfile GET /api/skills/inferen-sh-javascript-sdk/lockfile

Test it

Using "javascript-sdk". Add a secure inference.sh image generation task to a Node.js service.

Expected outcome:

Installation and private environment configuration steps.
A typed task flow with input validation and structured error handling.
Guidance for downloading the generated image with size and content checks.

Using "javascript-sdk". Plan a customer support agent that can notify Slack after approval.

Expected outcome:

An agent design with scoped tools and persistent session handling.
A confirmation step before sending the Slack notification.
Host restrictions, payload validation, redaction, and audit log recommendations.

Security Audit

High Risk

v5 • 8/6/2026 Open versioned report

Most static matches are documentation syntax or legitimate SDK examples, including template literals, file operations, and server-side environment configuration. Confirmed risks include direct eval of agent input, an unpinned external skill install, broad package execution permissions, agent-callable webhooks, and a browser-exposed API key example.

Files scanned

3,961

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

High

SKILL.md:4

Broad Package Execution Permission

The skill permits unrestricted npm, npx, node, pnpm, and yarn commands. These patterns can execute arbitrary packages and lifecycle scripts with the agent process permissions.

The allowed-tools frontmatter explicitly grants wildcard package-manager and Node command access. Those commands can execute downloaded code without a command-specific allowlist.

Capability review items (7)

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

references/server-proxy.md:395

Generic API/secret keys

: { apiKey: process.env.NEXT_PUBLIC_INFERENCE_API_KEY })

The example places an inference API key in NEXT_PUBLIC_INFERENCE_API_KEY for direct browser use. Next.js exposes NEXT_PUBLIC values to client bundles, disclosing the credential.

High

references/tool-builder.md:240

Dynamic code evaluation with eval()

result = eval(call.args.expression);

The example passes an agent-supplied expression directly to eval(). A crafted tool argument can execute arbitrary JavaScript in the host process.

High

references/tool-builder.md:387

Dynamic code evaluation with eval()

const result = eval(call.args.expression);

The example passes an agent-supplied expression directly to eval(). A crafted tool argument can execute arbitrary JavaScript in the host process.

High

SKILL.md:7

Ruby/shell backtick execution

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

Line 7 instructs users to run an unpinned npx command that installs the external belt-sh/cli skill. This creates package and skill supply-chain exposure.

Medium

references/tool-builder.md:159

Slack webhook

const slack = webhookTool('notify_slack', 'https://hooks.slack.com/services/...')

The example configures an agent-callable Slack webhook, creating a real outbound side effect and potential data disclosure path. The displayed endpoint is only a placeholder.

Medium

references/tool-builder.md:360

Slack webhook

const slack = webhookTool('notify', 'https://hooks.slack.com/...')

The example configures an agent-callable Slack webhook, creating a real outbound side effect and potential data disclosure path. The displayed endpoint is only a placeholder.

Medium

SKILL.md:301

Slack webhook

const notify = webhookTool('slack', 'https://hooks.slack.com/...')

The example configures an agent-callable Slack webhook, creating a real outbound side effect and potential data disclosure path. The displayed endpoint is only a placeholder.

Risk Factors

⚙️ External commands (50)

📁 Filesystem access (16)

references/agent-patterns.md:153 references/agent-patterns.md:159 references/agent-patterns.md:166 references/agent-patterns.md:129 references/files.md:139 references/files.md:141 references/files.md:153 references/files.md:155 references/files.md:236 references/files.md:249 references/files.md:272 references/files.md:278 references/files.md:412 references/files.md:417 SKILL.md:352 SKILL.md:354

🔑 Env variables (50)

🌐 Network access (26)

⚡ Contains scripts (4)

references/tool-builder.md:240 references/tool-builder.md:387 references/typescript.md:316 references/typescript.md:320

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/inferen-sh-javascript-sdk/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/inferen-sh-javascript-sdk/security.svg)](https://skillstore.io/skills/inferen-sh-javascript-sdk?utm_source=security_passport_badge)

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/inferen-sh-javascript-sdk.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

inferen-sh. (2026). javascript-sdk security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inferen-sh-javascript-sdk/audits/5

BibTeX citation

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

Compare variants

2 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 Current

inferen-sh-javascript-sdk

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 10

Updated

2026-08-21

inference-sh-9

inference-sh-9-javascript-sdk

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 8

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Add AI Tasks to Node.js

Create a typed server integration that runs inference.sh applications and handles results, errors, and files.

Build a Streaming React Interface

Connect a React or Next.js interface through a server proxy and display incremental task progress.

Create an Approved Tool Agent

Design an agent with typed tools, sessions, and human confirmation for sensitive external actions.

Try These Prompts

Install and Run a Task

Set up @inferencesh/sdk in my Node.js project. Show a minimal task call using a server-side environment variable and explain each required value.

Add Streaming Progress

Convert my inference.sh task call to streaming mode. Handle status updates, partial output, completion, and errors without blocking the interface.

Integrate a Secure Next.js Proxy

Add an inference.sh proxy to my Next.js App Router project. Keep the API key server-side and include authentication, input validation, and rate limiting.

Design a Controlled Agent Workflow

Design a TypeScript inference.sh agent with typed tools and persistent sessions. Require approval for external actions, avoid eval, and define audit logging and failure handling.

Best Practices

Keep API keys in private server environments and expose browser clients only through authenticated proxies.
Validate tool arguments and require approval for filesystem, code execution, and external network actions.
Pin dependencies, handle streamed failures, and record task identifiers for operational tracing.

Avoid

Do not evaluate model-generated expressions or tool arguments with eval.
Do not place inference credentials in NEXT_PUBLIC variables or browser bundles.
Do not allow unrestricted webhooks, package commands, or destructive tools without validation and approval.