agent-bom ingest
Validate and import cloud asset inventory JSON to generate local 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 to generate local audit reports. Full Skill content: https://321skill.com/skills/agent-bom-ingest-x-11/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 challenge of securely auditing cloud asset inventory without direct cloud credentials. Users export standard JSON from platforms like AWS, Azure, and GCP, then need to locally validate, scan, and generate findings reports without exposing cloud credentials to third-party tools. In practice, operations teams often need to consolidate and analyze cross-platform inventory data but are concerned about credential leakage risks.
The workflow is straightforward: first, validate the JSON format and schema using agent-bom mcp validate inventory.json, then execute agent-bom scan --inventory inventory.json --format json --output findings.json for local scanning. Output can be generated in various formats as needed: SARIF (for CI integration), HTML (for manual review), Markdown (for documentation), or CycloneDX/S (for SBOM). The entire process requires no cloud credentials, relying solely on the user-provided inventory JSON file.
It is well-suited for operations engineers and data analysts requiring compliance audits and security investigations. Teams that already have standardized inventory JSON can perform localized analysis without sharing cloud credentials with third parties, generating traceable audit reports, dependency graphs, or policy validation results.
It is recommended to perform schema validation immediately after obtaining the inventory JSON to ensure data reliability. Note that this tool requires Python 3.11+ and agent-bom 0.84.4+, and the inventory JSON must strictly adhere to the packaged inventory.schema.json contract. Optional push to a control plane requires the operator to provide a URL and API token; avoid disclosing these sensitive details in conversations.
Key Features
Unlike tools like CloudMapper that require direct connections to cloud APIs, this solution supports local validation of a unified JSON format across multiple platforms (AWS, Azure, GCP, etc.), enabling scanning and audit exports without cloud credentials. It offers higher security and is suitable for offline environments.
Limitations
Requires Python 3.11+ and agent-bom 0.84.4+. The inventory JSON must strictly comply with the inventory.schema.json contract; otherwise, validation will fail. Optional push to a control plane requires the operator to provide a URL and token.
FAQ
Does using this Skill require cloud platform credentials?
No. It only processes the user-provided inventory JSON file and does not require any cloud credentials or actively connect to cloud platform APIs.
Which cloud platforms or data sources are supported?
Supports standard inventory JSON exported from AWS, Azure, GCP, Snowflake, CMDB, or endpoint collectors, provided it conforms to the schema contract.
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-11/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-11/raw/index.md