Skip to content
Agentmart
Submit a tool

aws-scan-security

Evaluate IAM posture, public exposure, and security service status of the current AWS account.

Skill by nirecom

IndexedMIT★ 3
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/nirecom-aws-scan-security

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Evaluate IAM posture, public exposure, and security service status of the current AWS account.

Use cases: cloud, security

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/aws-scan-security

What's inside

Skill name
aws-scan-security
Description
Evaluate IAM posture, public exposure, and security service status of the current AWS account.
License
MIT
Instructions
30 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

## Procedure

ASE-1. Verify prerequisites.
ASE-2. IAM posture (pass `--profile $AWS_PROFILE --region $AWS_DEFAULT_REGION`):
   - Root MFA: `aws iam get-account-summary --query 'SummaryMap.AccountMFAEnabled'`
   - Users without MFA: `aws iam list-virtual-mfa-devices --assignment-status Unassigned`
   - Admin policies on users: `aws iam list-attached-user-policies` per user, flag AdministratorAccess
   - Access keys >90 days: `aws iam list-access-keys`, check CreateDate
ASE-3. Public exposure:
   - Public S3: `aws s3api get-bucket-acl` + `aws s3api get-bucket-policy-status` per bucket
   - SGs 0.0.0.0/0 on 22/3389/3306/5432: `aws ec2 describe-security-groups --filters Name=ip-permission.cidr,Values=0.0.0.0/0`
   - Public RDS: `aws rds describe-db-instances --query 'DBInstances[?PubliclyAccessible==\`true\`]'`
ASE-4. Security services: CloudTrail, GuardDuty, AWS Config, Security Hub (describe/list/get commands)
ASE-5. Write raw findings to `$AWS_STATE_DIR/security-<YYYYMMDD>.json` (severity: critical/high/medium/low).
ASE-6. Write human-readable summary to `$AWS_STATE_DIR/security-<YYYYMMDD>.md`:
   - Severity table: critical/high/medium/low counts
   - One bullet per finding category (no identifiers)
ASE-7. Print: counts by severity only — no identifiers.

## Rules

- Read-only only. Identifiers must NOT appear in conversation.
- Critical findings must be highlighted.
- AccessDeniedException → mark as unknown (not pass).

## Skip Conditions

Skip if `$AWS_STATE_DIR/security-<YYYYMMDD>.json` exists and is less than 4 hours old.

From nirecom/agents, MIT.

More from nirecom/agents

Signals

Stars
3
Forks
0
Open issues
608
Last commit (this folder)
Sep 29, 2026 (29 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/nirecom/agents
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from nirecom

Cite this page

aws-scan-security skill. Agent Mart. https://agentmart.dev/skills/nirecom-aws-scan-security (last updated 2026-10-24)