aws-cleanrooms

An agent skill by aws, from aws/agent-toolkit-for-aws. Tags: aws, compliance, ml, security, troubleshooting.

What it does

Troubleshoots and debugs AWS Clean Rooms collaboration issues related to IAM roles, S3 bucket policies, KMS keys, Lake Formation permissions, and CloudWatch logging for custom ML model training and inference jobs. Use when a customer reports permission failures, access errors, or log publishing issues in Clean Rooms.

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-cleanrooms

Or 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/skills/specialized-skills/analytics-skills/aws-cleanrooms ~/.claude/skills/aws-cleanrooms

Safety box score

Grade B, low risk: 19 of 100 risk points, rated 2026-10-16. 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 read-heavy AWS Clean Rooms troubleshooting guide that drives the agent to query Clean Rooms, IAM, S3, KMS, Lake Formation, Glue, and CloudWatch via AWS CLI. The main risk is broad exposure of account and infrastructure metadata through live AWS API calls; it does not include code execution, file edits, or direct destructive actions.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	1 (low)	It repeatedly instructs the agent to run shell/AWS CLI commands such as `aws sts get-caller-identity` and `aws iam get-role`, but it does not ship scripts or evaluate arbitrary code.
Network access	2 (moderate)	The skill sends live requests to AWS services (`aws cleanroomsml ...`, `aws iam ...`, `aws s3api ...`, `aws kms ...`, `aws logs ...`), so account metadata, policy contents, and resource details leave the machine to AWS.
Filesystem reach	0 (none)	There are no commands to read, write, or delete local files outside the project; the workflow stays in AWS APIs.
Secrets & credentials	1 (low)	It uses the operator's existing AWS credentials implicitly through the CLI and checks identity with `aws sts get-caller-identity`, but it does not ask to paste secrets or read local key stores explicitly.
Privilege & persistence	0 (none)	The skill does not require sudo, install software, register services, or modify shell/OS settings.
Instruction hijack surface	0 (none)	There is no prompt-injection content, hidden instruction, or request to ignore higher-priority rules; the markdown only contains normal troubleshooting steps.
Irreversible actions	1 (low)	It is diagnostic and asks for confirmation on ambiguous resources, though it also says to provide the exact policy fix and CLI commands, which could lead to privilege changes if the user applies them.
Transparency	0 (none)	All files are readable markdown; there are no binaries, base64 blobs, or downloaded/decoded runtime components.

Before installing

Confirm the agent will only use read-only AWS permissions in the target account.
Check whether you are comfortable with it querying IAM, KMS, S3, Lake Formation, Glue, CloudWatch, and Clean Rooms metadata.
Run it first in a sandbox or non-production AWS account if possible.
Review the active AWS profile/role so `aws sts get-caller-identity` will not expose an unexpected privileged account.

Rated 2026-10-16 by an automated review of 3 files from the skill's repository.

Source

Repository: aws/agent-toolkit-for-aws (all skills from this repository)
Path: skills/specialized-skills/analytics-skills/aws-cleanrooms/SKILL.md
Branch: main
Updated: 2026-09-19

aws-security — Covers AWS security services and workflows — Security Hub V2 (OCSF) findings, connectors, aggregators, automation rules, and security posture summaries.
amazon-ses — Guides Amazon SES onboarding for domain-based email sending.
creating-secrets-using-best-practices — Creates and manages secrets in AWS Secrets Manager following security best practices.
securing-s3-buckets — Create and secure S3 buckets following AWS best practices for access control, encryption, monitoring, and remediation of misconfigurations.
setting-up-cloudtrail-multi-region — Enables a multi-region AWS CloudTrail trail with S3 log storage, CloudWatch Logs integration.
aws-iam — Provides verified corrections for IAM behaviors that AI agents frequently get wrong — policy evaluation edge cases, trust policy gotchas, STS session limits.