Integrations

agent-bom discover aws

Try it

Discover AWS-hosted AI agent and MCP-relevant assets from the operator's environment, emit canonical agent-bom inventory JSON, and scan it without giving agent-bom long-lived cloud credentials. Use when a user asks to inventory AWS Bedrock, ECS, SageMaker, Lambda, EKS, Step Functions, EC2, or agentic AWS infrastructure as canonical inventory. Passing that inventory to agent-bom is optional and operator-chosen.

What it does

Discover AWS-hosted AI agent and MCP-relevant assets from the operator's environment, emit canonical agent-bom inventory JSON, and scan it without giving agent-bom long-lived cloud credentials. Use when a user asks to inventory AWS Bedrock, ECS, SageMaker, Lambda, EKS, Step Functions, EC2, or agentic AWS infrastructure as canonical inventory. Passing that inventory to agent-bom is optional and operator-chosen.

The skill document

agent-bom-discover-aws

Use this skill to collect AWS AI and workload inventory from the operator's environment as canonical inventory. The skill is discover-only by default: write schema-valid JSON to an operator-selected path and stop. Run agent-bom only when the operator explicitly wants findings, graph, policy, or exports from that inventory.

Guardrails

  • Use only operator-approved AWS profiles, roles, or short-lived STS sessions.
  • Prefer read-only IAM actions listed by agent-bom trust or /v1/discovery/providers.
  • Do not request or display raw AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_SESSION_TOKEN, or bearer tokens.
  • Do not modify AWS resources. This workflow is discovery-only.
  • Write inventory only to a path the operator chose.
  • Treat AI-generated prose as non-authoritative; only the schema-validated inventory JSON is evidence.

Modes

ModeWhat happensData boundary
discover-onlyEmit canonical inventory JSON and stopNo agent-bom scan or API handoff
scan-localRun agent-bom scan --inventory ... on the generated fileLocal handoff into the scanner
exportWrite JSON/SARIF or another operator-selected outputLocal output only unless the operator routes it elsewhere

Use discover-only unless the operator asks for scan results or an export.

Workflow

  1. Confirm the AWS account/region/profile and intended services.
  2. Generate inventory with the repository adapter and stop:
python examples/operator_pull/aws_inventory_adapter.py \
  --region us-east-1 \
  --profile readonly-audit \
  --source aws-skill-invoked \
  --discovery-method skill_invoked_pull \
  --output aws-inventory.json
  1. If the operator asks for findings, scan the generated inventory locally:
agent-bom scan --inventory aws-inventory.json
  1. If the operator asks for an export, write it to an operator-selected path:
agent-bom scan --inventory aws-inventory.json --format json --output agent-bom-aws-findings.json

Optional Service Flags

Start narrow, then expand deliberately:

python examples/operator_pull/aws_inventory_adapter.py \
  --region us-east-1 \
  --profile readonly-audit \
  --source aws-skill-invoked \
  --discovery-method skill_invoked_pull \
  --include-ecs \
  --include-lambda \
  --include-eks \
  --output aws-inventory.json

Use --no-include-ecs or similar flags to disable default services when an operator wants a smaller scope.

Evidence Contract

The inventory emitted by this skill uses:

  • source: aws-skill-invoked
  • discovery_provenance.source_type: skill_invoked_pull
  • discovery_provenance.observed_via: skill_invoked_pull, aws_sdk
  • sanitized metadata.permissions_used
  • sanitized cloud_origin, cloud_principal, lifecycle fields, packages, and MCP server launch metadata

If schema validation fails, stop and fix the inventory instead of scanning a best-effort or prose summary.

The skill does not push inventory to an API by default. Any push, scan, or managed control-plane handoff must be a separate operator-approved handoff command with the destination URL, auth method, and retained evidence classes made explicit.

Related skills

Discover Azure-hosted AI agent and MCP-relevant assets from the operator's environment, emit canonical agent-bom inventory JSON, and scan it without giving agent-bom long-lived Azure credentials. Use when a user asks to inventory Azure OpenAI, Container Apps, AKS, Functions, ML, or agentic Azure infrastructure as canonical inventory.

37 installs

Discover GCP-hosted AI agent and MCP-relevant assets from the operator's environment, emit canonical agent-bom inventory JSON, and scan it without giving agent-bom long-lived GCP credentials. Use when a user asks to inventory Vertex AI, Cloud Run, Cloud Functions, GKE, or agentic GCP infrastructure as canonical inventory.

38 installs

Validate and ingest operator-pushed agent-bom inventory JSON from AWS, Azure, GCP, Snowflake, CMDB, or endpoint collectors. Use when a user has canonical inventory JSON and wants local findings, graph, policy, provenance, or auditor-ready exports without giving agent-bom direct cloud credentials.

38 installs

Discover Snowflake Cortex, Snowpark, notebook, Streamlit, MCP, and AI-observability assets from the operator's environment, emit canonical agent-bom inventory JSON, and scan it without giving agent-bom long-lived Snowflake credentials. Use when a user asks to inventory Snowflake AI or Cortex infrastructure as canonical inventory.

38 installs

MCP server security registry and trust assessment — look up servers in the 1123-entry server security metadata registry, run pre-install marketplace checks, batch fleet risk scoring, assess skill file trust, and run SAST code scans. Use when the user mentions MCP server trust, registry lookup, marketplace check, or skill trust assessment.

73 installs

AI runtime security monitoring — context graph analysis, runtime audit log correlation with CVE findings, and vulnerability analytics queries. Use when the user mentions runtime monitoring, context graphs, lateral movement analysis, audit log correlation, or vulnerability analytics.

73 installs