agent-bom discover aws
Discover AWS AI assets and generate a standardized inventory.
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 discover aws. It is used for: Discover AWS AI assets and generate a standardized inventory. Full Skill content: https://321skill.com/skills/agent-bom-discover-aws-x-8/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 quickly discovering and inventorying AI Agent and MCP-related assets within the AWS cloud environment. In real-world operations or development, teams often need to audit resources such as Bedrock Agents, ECS services, SageMaker endpoints, Lambda functions, EKS clusters, Step Functions state machines, and EC2 instances. Traditional methods either rely on long-term credentials, posing security risks, or produce inconsistent output formats that are difficult to integrate into subsequent compliance scanning or cost analysis workflows.
Usage is straightforward: simply run this skill in an environment where the AWS SDK credential chain is configured (preferring AWS SSO, WebIdentity, or STS short-term credentials). It will automatically invoke read-only APIs to scan services in the specified region, generate a JSON inventory file compliant with the agent-bom specification, and save it to your designated path. You can then optionally pass this inventory to agent-bom for vulnerability scanning, policy auditing, or report generation. The entire process avoids exposing long-term cloud credentials to agent-bom.
It is ideal for operations engineers and agent development teams who need to regularly inventory their AWS AI infrastructure. Particularly for organizations already using agent-bom for security and compliance management, this skill enables rapid establishment of an asset baseline, eliminating omissions and errors from manual data collection. For scenarios requiring compliance with SOC2, ISO27001, or similar audit standards, this automated inventory generation capability significantly improves efficiency.
Before use, it is recommended to ensure the AWS IAM policy grants read-only permissions and to prioritize temporary credentials. Note that this skill currently only supports discovery operations and will not modify any assets. It requires a Python 3.11+ environment and the agent-bom library, which must be installed via pip before first use. If operating in a restricted network environment, confirm that access to STS and the API endpoints of the target services is available.
Key Features
Unlike AWS Config or AWS Resource Explorer, it specifically focuses on AI Agent and MCP-related assets (e.g., Bedrock, SageMaker, Lambda) and outputs directly in agent-bom's compliant JSON format, eliminating the need for secondary conversion. Additionally, it leverages local SDK calls to avoid passing long-term credentials to third-party tools.
Limitations
Requires Python 3.11+ environment, depends on the agent-bom library (installable via PyPI), only supports the AWS SDK credential chain (SSO/WebIdentity/STS), and is limited to read-only discovery operations; it cannot write to or modify AWS resources.
FAQ
What AWS permissions are required?
A read-only IAM policy is recommended. For specific permissions, refer to the operations list provided by the agent-bom trust command or /v1/discovery/providers.
How do I install agent-bom?
Execute `pip install agent-bom`. This skill is used as a subcommand or plugin of agent-bom.
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-discover-aws-x-8/raw/index.md to read the original Skill definition (Markdown format) for agent-bom discover aws, and install it according to the instructions.
Raw Markdown URL for AI: /skills/agent-bom-discover-aws-x-8/raw/index.md