security-engineer

Assess AWS security posture and triage findings across IAM, GuardDuty, Security Hub, and Inspector.

3|1|Updated Feb 14, 2026
One-click install
npx skills add https://github.com/LiboMa/agenticops-chat --skill security-engineer-liboma
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: security-engineer
Source: https://github.com/LiboMa/agenticops-chat/tree/main/skills/security-engineer
Command: npx skills add https://github.com/LiboMa/agenticops-chat --skill security-engineer-liboma

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? AWS environments accumulate security risks across many services — overprivileged IAM roles, public S3 buckets, open security groups, unpatched CVEs, and active threats — and manually auditing each one with the CLI is slow and error-prone. This Skill provides structured decision trees, ready-to-run AWS CLI commands, and severity-based triage playbooks so you can assess posture and respond to incidents systematically. ## Core Features & Use Cases - IAM Security Assessment: Audit credential hygiene (MFA gaps, stale keys, root access keys), detect overprivileged policies and privilege-escalation paths, and review cross-account trust relationships. - Threat & Finding Triage: Prioritize GuardDuty findings by type and severity, triage Security Hub CIS benchmark failures, and rank Inspector CVEs using a CVSS/network-reachability/exploit-availability matrix. - Configuration & Compliance Audits: Check S3 public access, security groups and NACLs with 0.0.0.0/0 exposure, KMS key rotation, EBS/RDS/S3 encryption, CloudTrail integrity, WAF rules, and AWS Config compliance. - Incident Response: Isolate compromised EC2 instances with quarantine security groups, disable compromised IAM credentials, and create forensic snapshots before termination. - Use Case: After a GuardDuty CRITICAL finding for UnauthorizedAccess:IAMUser, follow the playbook to look up the principal's CloudTrail activity, check for persistence mechanisms, disable the credentials, and verify no new access keys were created. ## Quick Start Ask the agent to run a security posture review of my AWS account covering IAM credential hygiene, open security groups, public S3 buckets, and active GuardDuty and Security Hub findings.

Frequently Asked Questions about security-engineer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I audit IAM users for missing MFA and stale access keys in AWS?▼

Generate the IAM credential report with aws iam generate-credential-report, then retrieve it with aws iam get-credential-report. Flag users where password_enabled is true but mfa_active is false, and any access keys or console passwords unused for more than 90 days.

How do I triage GuardDuty findings by severity?▼

List findings with a severity filter of 7 or higher using aws guardduty list-findings, then classify them by type prefix. UnauthorizedAccess, Trojan, Backdoor, and Exfiltration types are critical, while Recon findings are typically medium severity and reviewed for security group exposure.

How do I find security groups open to 0.0.0.0/0 on sensitive ports?▼

Run aws ec2 describe-security-groups with a JMESPath query filtering IpPermissions for CidrIp 0.0.0.0/0. Ports 22, 3389, 3306, 5432, 6379, and 27017 exposed to the internet are critical risks and should be restricted immediately.

How should I prioritize Inspector vulnerability findings for patching?▼

Prioritize using three factors: CVSS score, network reachability, and exploit availability. Findings with CVSS 9.0 or higher that are network reachable with a known exploit are P0 and should be patched within 24 hours; lower scores without reachability go to the backlog.

What should I do first when an EC2 instance is compromised?▼

Isolate the instance immediately by replacing its security groups with an empty quarantine group, then create forensic EBS snapshots before any termination. Afterward investigate how it was compromised by checking the instance profile permissions, public IP exposure, and open ports.

Does this skill make changes to my AWS account automatically?▼

Most assessment commands are read-only describe, list, and get API calls. Remediation actions like disabling access keys, modifying security groups, or creating snapshots are provided as explicit commands for you to run, so nothing changes without deliberate execution.