cloud-iam-deep is a skill for Claude that covers what to do when an authorized assessment turns up a cloud credential: an access key, a service account file, a token or a metadata endpoint reachable through another flaw. It starts with recognizing the credential type, then validates it with read-only identity and policy calls and works out what the identity can reach.
The skill covers AWS role chaining and metadata service behavior, Azure managed identities and RBAC, GCP service accounts, exposed Kubernetes tokens and unauthenticated Cognito identity pools. It also gives severity guidance and a cleanup discipline for the deliverable.
What You Get
- Credential recognition patterns for AWS, Azure, GCP and Kubernetes
- A read-only first-step checklist for identity, policies and service surface on each cloud
- Notes on role chaining, cross-account trust and metadata service behavior
- A tooling reference, anti-patterns and severity scoring guidance
- A cleanup discipline for what goes into the deliverable
Common Use Cases
- Finding out what a leaked key from a mobile app or repository can reach during an authorized test
- Writing up the impact of a server-side request flaw that reaches a cloud metadata endpoint
- Reviewing the trust relationships between accounts in a client’s AWS organization
What Makes It Unique
It begins with what the identity is and what it can do before anything else, and treats read-only validation as the first step. It ties the cloud work back to the external-testing boundary of the bundle and to the web skills that surface credentials, such as SSRF and source-leak hunts.
Under The Hood
The skill is a single SKILL.md of instructions with no bundled scripts. Following it, the agent runs cloud command-line tools such as the AWS, Azure and Google Cloud CLIs, sets credential environment variables on your machine and makes network calls to the cloud control plane and metadata endpoints with a credential that was found during testing. It may also query a Kubernetes API with a service-account token. The text lists key and token patterns to recognize, and one example service-account file in it holds only placeholder values, with a private-key header and dots in place of a key. It asks for cleanup of anything created. Use it only with credentials and accounts you are authorized to test.