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.
Integrations
agent-bom discover aws
Try itDiscover 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 trustor/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
| Mode | What happens | Data boundary |
|---|---|---|
discover-only | Emit canonical inventory JSON and stop | No agent-bom scan or API handoff |
scan-local | Run agent-bom scan --inventory ... on the generated file | Local handoff into the scanner |
export | Write JSON/SARIF or another operator-selected output | Local output only unless the operator routes it elsewhere |
Use discover-only unless the operator asks for scan results or an export.
Workflow
- Confirm the AWS account/region/profile and intended services.
- 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
- If the operator asks for findings, scan the generated inventory locally:
agent-bom scan --inventory aws-inventory.json
- 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-invokeddiscovery_provenance.source_type: skill_invoked_pulldiscovery_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 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.
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.
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.
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.
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.