Home / Claude Code skill packs
aws-security-skills
AWS security skills for Claude Code: account audit, SCP guardrails, blast-radius landing zones, IAM least privilege, Security Hub triage.
What it is
AWS security skills for Claude Code: account audit, SCP guardrails, blast-radius landing zones, IAM least privilege, Security Hub triage, agent-safe access, incident response runbooks, spend guardrails, sandbox guardrails, agent session audit, preventive controls for Security Hub findings.
aws-security-skills is a Claude Code plugin marketplace with one plugin, aws-security, holding eleven skills. Each skill is a fixed procedure plus a tested Python script (standard library only). The skills tell Claude which read-only aws CLI commands to run and where to save the JSON, or which short spec to write; the scripts then evaluate that saved output, or generate policies and runbooks from the spec, offline, so results are repeatable, reviewable by someone without account access, and produced without the script ever touching AWS.
It is written for cloud and platform engineers who look after one or many AWS accounts, especially multi-account organizations governed by service control policies. It exists because the same questions come up on every account (is root protected, is CloudTrail on, can this role escalate, which SCPs go where, what do we fix first in Security Hub, what may an AI agent do here, what do we do in the first hour of an incident, how do we stop a runaway bill), and a scripted procedure answers them the same way each time.
Common searches it answers: a CIS AWS Foundations benchmark style account check, a Well-Architected security pillar review of account structure, a permission boundary for an AI agent role, and an audit of what an AI agent did in an AWS account from CloudTrail ("what did the agent do in our AWS account?", unused permissions of an agent role), and the preventive control for a failing Security Hub control ("how do we stop this finding coming back?", SCP, declarative policy and IaC check for S3, EBS, IMDSv2 and root user findings).
No network access from the scripts, no telemetry. Nothing in this repository changes an AWS account: every skill proposes fix commands and runs one only after you confirm that exact command.
Install
/plugin marketplace add basitalisandhu/aws-security-skills
/plugin install aws-security@aws-security-skills
From the README; see the full README for every option.
Links
Releases
Posts about it
- Four open repositories for securing AI agents, and what each is for
A map of the open tools for AI agent security: an incident dataset, Semgrep rules for agent code, a threat-model CLI and Claude Code skill packs, with where each one stops. - Every Claude Code skill I maintain, in one repository
87 Claude Code skills in 13 plugins from 8 source repositories, now in one repository with one marketplace and one install script.
More in Claude Code skill packs
- claude-skills: Every skill I maintain, in one repository: 87 skills in 13 plugins from the packs below, one marketplace, one install script, synced daily.
- ways-of-working-skills: Claude Code skills for ways of working: change requests from a Terraform plan, an action ledger across meeting notes, exception and risk registers, RFC lint, a decision log, weekly status notes, a private 1:1 ledger and focus time from a calendar export.
- repo-engineering-skills: Repository engineering skills for Claude Code: docs checked against the code, audits where every finding cites a line, agent context files that say only what code cannot.
- m365-governance-skills: Microsoft 365 governance skills for Claude Code: Entra ID posture review, Intune baseline check, Graph permission preflight, Teams and group sprawl, access review pack.
- compliance-evidence-skills: Compliance evidence skills for Claude Code: integrity-checked evidence packs from GitHub, AWS and Microsoft 365 exports, mapped to ISO 27001 and SOC 2, with narratives that cite evidence or say not assessable.
- claude-dev-skills: Claude Code skills for everyday development: code review, refactoring, debugging, CI and containers, data and APIs, documentation and security basics.
- agent-security-skills: Claude Code security plugin and agent skills for securing LLM agents: threat modelling, configuration audits, prompt injection review, MCP server review, incident lookup.
- github-manager-skills: Claude Code skills for engineering managers that compute from exported GitHub data: stuck-PR and review-queue digest, iteration report, blameless postmortem timeline.
- mac-maintenance-skills: Claude Code skills for cleaning up and speeding up a Mac: read-only survey first, safe tier removes only what programs recreate, leftovers and duplicate finders.
- claude-code-tooling-skills: Claude Code skills for keeping a Claude Code setup safe: review a third-party skill before installing it, lint skill descriptions, audit the context budget, build least-privilege permissions, test hooks.
- agent-identity-governance-skills: Claude Code skills for agent identity governance: inventory the non-human identities agents run as, review permissions, recertify quarterly, catch expiring credentials, switch one off fast.
Topics: agent-skills, aws, aws-organizations, aws-security, claude-code, claude-code-plugin, cloud-security, cspm, devsecops, guardduty, hacktoberfest, iam, landing-zone, least-privilege, python, security-hub, security-tools, service-control-policies