aws-cloudformation
An agent skill by aws, from aws/agent-toolkit-for-aws. Tags: cloud, devops, infrastructure, security, validation.
What it does
Authors, validates, and troubleshoots AWS CloudFormation templates. Covers template authoring with secure defaults, local validation with either cfn-lint or cloudformation-validate, cfn-guard security and compliance checks as a recommended default, account-aware CloudFormation service pre-deployment validation, CloudFormation Express mode for faster deployments, and root-cause diagnosis of failed stacks using CloudFormation events and CloudTrail correlation. Also covers author-time template intelligence with the CloudFormation Language Server and published cloudformation-validate libraries.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add aws/agent-toolkit-for-aws --skill aws-cloudformationOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/aws/agent-toolkit-for-aws
cp -r agent-toolkit-for-aws/plugins/aws-core/skills/aws-cloudformation ~/.claude/skills/aws-cloudformationSafety box score
Grade D, elevated risk: 56 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill is a full CloudFormation operator: it reads and annotates templates, runs local and account-aware validation, and can create, update, delete, and troubleshoot stacks through AWS APIs. The main risks are broad AWS-side blast radius, network egress of templates and account metadata, and destructive deployment actions if it is used with live credentials.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 2 (moderate) | It drives shell-style commands and validators such as `cfn-lint --format json`, `aws cloudformation describe-events`, and even install commands like `pip install --upgrade awscli`, so it can execute real tooling on the user's machine. |
| Network access | 3 (high) | It sends templates and stack/account metadata to AWS services (`call_aws`, AWS CLI, CloudTrail, S3/CloudFormation) and may download external tooling or rules from PyPI and GitHub, so its network reach is broad. |
| Filesystem reach | 2 (moderate) | It reads local template files, can add `Metadata` to templates, and tells the user to edit workspace/config files such as `.kiro/settings/lsp.json`, so it can write in the user's filesystem. |
| Secrets & credentials | 2 (moderate) | It requires valid AWS credentials for account-aware operations (`aws sts get-caller-identity`) and handles template/metadata content that must not contain secrets, so it interacts with credentialed account data even though it warns against storing secrets. |
| Privilege & persistence | 1 (low) | It does not require sudo or OS service registration, but it can change local editor/config files and AWS account configuration through approved operations. |
| Instruction hijack surface | 1 (low) | The skill explicitly treats template text as untrusted and has no hidden payloads, but it also depends on external docs/rules and remote references, so upstream content can influence behavior if not reviewed. |
| Irreversible actions | 3 (high) | Its purpose includes live infrastructure actions such as `create-stack`, `update-stack`, `delete-stack`, `create-change-set`, `execute-change-set`, and Express-mode deployment, which are high-blast-radius operations even with approval gates. |
| Transparency | 0 (none) | All shipped files are readable markdown; I found no binaries, minified blobs, or decoded-at-runtime code. |
Before installing
- Decide whether you want this skill to have live AWS write access; if not, keep AWS credentials unavailable in the session.
- Review `SKILL.md` plus `references/deploy-with-express-mode.script.md` and `references/cloudformation-pre-deploy-validation.script.md` before allowing any deployment workflow.
- If you will use it locally, test first in a scratch AWS account with least-privilege credentials and no production stack names.
- Confirm you are comfortable with the skill writing to template files and local config such as `.kiro/settings/lsp.json` before enabling it.
Rated 2026-10-20 by an automated review of 16 files from the skill's repository.
Source
- Repository
- aws/agent-toolkit-for-aws (all skills from this repository)
- Path
- plugins/aws-core/skills/aws-cloudformation/SKILL.md
- Branch
- main
- Collection
- aws-core
- Updated
- 2026-09-19
Related skills
- aws-cdk — Authors, deploys, and troubleshoots AWS infrastructure using CDK with TypeScript or Python. Covers best practices, stack architecture, and construct patterns.
- aws-iam — Provides verified corrections for IAM behaviors that AI agents frequently get wrong — policy evaluation edge cases, trust policy gotchas, STS session limits.
- agents-harden — Use when preparing your agent for production — IAM scoping, inbound auth (JWT, SigV4), secrets management, cold start optimization, session lifecycle.
- agents-pay — Use when THIS agent needs to pay for x402-protected content at runtime: hitting a paywall mid-task, settling it via AgentCore Payments.
- pentesting-with-aws-security-agent — Run an AWS Security Agent penetration test against a live web application — registers and verifies the target domain.
- scanning-with-aws-security-agent — Run an AWS Security Agent scan on the workspace — uploads the source to AWS, scans it with the managed Security Agent service, and returns ranked.