Skip to content
SkillModel-led6,475 tokens in use

cloud-iam-deep

Cloud IAM review for AWS, Azure and GCP in authorized engagements: identify a discovered credential, check its permissions with read-only calls, trace role chains and clean up.

14,523 stars on the repository MIT Licenseelementalsouls/Claude-BugHunter · skills/cloud-iam-deep
/plugin marketplace add elementalsouls/Claude-BugHunter /plugin install claude-bughunter@elementalsouls
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing cloud-iam-deep costs

237tokens idle
6,475tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetectednetworkdetectedwrites filesdetectedcredentialsdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure25/25
  • Examples12/15
  • Output15/15
  • Size11/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Needs attention
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 28
  • Key or token in a file−30

    a key or token written into the file

    SKILL.md, line 47
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 133
  • Reaches the network−10

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 158
  • Reads credentials−15

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 428

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance84
  • Community68
  • Maturity28
  • Momentum40

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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers