agent-bom ingest
Validate and import cloud asset inventory JSON, generate audit reports offline
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, generate audit reports offline Full Skill content: https://321skill.com/skills/agent-bom-ingest-x-7/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 pain point of security auditing for cloud asset inventory data. In actual operations, teams often export standardized inventory JSON from cloud platforms like AWS, Azure, GCP, or from a CMDB. However, directly feeding this JSON to an AI or third-party tools poses credential leakage risks. With agent-bom ingest, you can locally validate the integrity of the inventory JSON and perform scans without any cloud credentials, generating findings, graphs, compliance reports, and audit exports.
Usage is straightforward: you only need to prepare an inventory JSON file that conforms to the inventory.schema.json format. You can then execute validation and scans using natural language commands. For example, first run agent-bom mcp validate inventory.json to check the JSON's schema compliance, then run agent-bom scan --inventory inventory.json --format json --output findings.json to output local findings. It supports export to formats like SARIF, HTML, Markdown, and CycloneDX to meet various audit scenarios.
It is well-suited for operations engineers and security teams needing to perform security audits on cloud infrastructure. This is especially true for teams that have already collected cloud asset inventories using agent-bom or other tools but wish to conduct local compliance checks, risk analysis, and report generation without exposing cloud credentials. For scenarios requiring regular submission of audit reports to regulators, this Skill can significantly improve efficiency.
It is recommended to integrate this tool into a unified security workflow, such as automatically triggering inventory validation within a CI/CD pipeline. Note that it primarily relies on Python 3.11+ and agent-bom 0.84.4+, and the inventory JSON must strictly adhere to the packaged schema contract. Optional control plane push requires the user to provide an API token—ensure this token is never leaked in chat.
Key Features
Unlike CloudQuery, which requires configuring cloud connections, agent-bom ingest directly uses exported inventory JSON, performing all validation and scanning offline without any cloud credentials, offering higher security. It also supports formats like SARIF and CycloneDX, enabling direct integration with CI/CD audit gates.
Limitations
Requires Python 3.11+ and agent-bom 0.84.4+. The inventory JSON must strictly comply with the packaged `inventory.schema.json` contract. It does not support real-time cloud asset fetching; an inventory file must be available first.
FAQ
How do I obtain the inventory JSON file?
You first need to export the inventory JSON using the cloud platform's CLI or agent-bom's pull function. For example, use AWS CLI or Azure CLI to export the resource list, then save it as a local file.
Which cloud platforms does agent-bom ingest support?
It supports inventory JSON exported from AWS, Azure, GCP, Snowflake, CMDB, and endpoint collectors, as long as the format conforms to the schema.
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-7/raw/index.md to read the original Skill definition (Markdown format) for agent-bom ingest, and install it according to the instructions.
Raw Markdown URL for AI: /skills/agent-bom-ingest-x-7/raw/index.md