En

agent-bom ingest

Validate and import cloud asset inventory JSON, perform local scanning to generate audit reports.

Install & Use

Copy this prompt and send it to your AI assistant (Claude / Cursor / TRAE / Codex / WorkBuddy etc.) to auto-install:

Help me install this AI Skill: agent-bom ingest.
It is used for: Validate and import cloud asset inventory JSON, perform local scanning to generate audit reports.
Full Skill content: https://321skill.com/skills/agent-bom-ingest-x-3/raw/index.md
Read that page and install it.

The prompt includes a link to the full Skill content. You can also view the full content.

This Skill addresses the need for secure, offline processing of multi-platform inventory JSON files in cloud asset auditing. In real-world operations, teams often export asset inventories from platforms like AWS, Azure, GCP, or CMDBs. However, scanning directly using cloud credentials poses security risks, and a unified format is required for compliance analysis.

Usage is straightforward: simply prepare a JSON file conforming to the schema, then run agent-bom mcp validate inventory.json to verify the format, followed by agent-bom scan --inventory inventory.json --format json --output findings.json to perform a local scan. Afterward, you can use natural language commands to export reports in formats like SARIF, HTML, or Markdown for auditing, policy checks, or graph analysis.

It is ideal for teams or individuals needing unified auditing of multi-cloud assets and enhanced security compliance, especially those who have already generated standard JSON via endpoint collectors or CMDBs. Whether for security audits by operations engineers or compliance reporting by project managers, deep analysis can be completed without exposing cloud credentials.

It is recommended to use this tool after standardizing the asset inventory schema, ensuring the JSON strictly adheres to inventory.schema.json. Note that it primarily relies on local scanning capabilities; optional vulnerability queries will call external OSV and GitHub Advisory APIs but will not upload your asset data. Control plane pushes require the user to provide a URL and Token, and credentials must never be disclosed in conversations.

Key Features

Unlike directly scanning cloud accounts with agent-bom, this Skill focuses on offline import of existing JSON, assessing data credibility through schema validation without requiring any cloud credentials. It supports inventory formats from multiple sources including AWS, Azure, GCP, Snowflake, and CMDBs.

Limitations

Requires Python 3.11+ and agent-bom 0.84.4+. Local scanning optionally depends on external vulnerability query APIs. JSON must conform to the packaged schema, otherwise validation will fail.

FAQ

Are cloud platform accounts or credentials required?

No. This Skill only processes user-provided JSON files and does not connect directly to cloud platforms, so no cloud credentials are needed.

What output formats are supported?

Supports JSON, SARIF, HTML, Markdown, CycloneDX/SPDX, and other formats, suitable for CI integration, manual review, and automated processes.

Installation guide for AI assistants

If your AI coding assistant (Claude Code, Cursor, TRAE etc.) can see this page, send it this message to auto-install:

Visit https://321skill.com/skills/agent-bom-ingest-x-3/raw/index.md to read the original Skill definition (Markdown format) for agent-bom ingest, and install it according to the instructions.