AWS IR Pack: GuardDuty + CloudTrail Incident Response
AWS IR Pack gives an agent the incident-response workflow for AWS, start to finish.
$19
Works with the AI Agents you already use
AWS IR Pack: GuardDuty + CloudTrail Incident Response
Example session with this skill installed
Triage this GuardDuty finding and walk me through response. No live AWS access.
(paste examples/findings/01-instance-cred-exfil.json — instance-role credentials used from an IP outside AWS)
- Read your context and instructions
- Compiled the aws ir
Verdict: True Positive, high confidence. Type UnauthorizedAccess:IAMUser/InstanceCredentialExfiltration.OutsideAWS. ATT&CK T1552.005 + T1078.004. Evidence: temporary key of the instance role used from a hosting ASN outside AWS. Next: check IMDSv1/SSRF on the source instance; run the bundled CloudTrail queries on the access key and source IP; run the privilege-escalation module on the instance role. Proposed containment, each gated on CONFIRM <id>: snapshot evidence, revoke role sessions with AWSRevokeOlderSessions, enforce IMDSv2, optionally isolate the instance. The skill must not try to deactivate an ASIA temporary key with update-access-key, and must not run a change without CONFIRM.
Connects securely to your tools. The creator never sees your data.
About this skill
A GuardDuty alert at 2 a.m. should not send you hunting through docs. AWS IR Pack gives an agent the incident-response workflow for AWS, start to finish.
Triage. Playbooks for 20 high-signal GuardDuty types — credential exfiltration, C2, crypto-mining, Tor, brute force, S3 exposure, root use, logging disabled, anomalous IAM behavior — with false-positive heuristics and a MITRE ATT&CK mapping.
Timeline. Copy-paste Athena SQL for CloudTrail and VPC Flow Logs, CloudWatch Logs Insights queries, and lookup-events fallbacks, pivoting on access key, IP, role session, instance, and bucket.
Containment. AWS CLI playbooks for EC2 isolation via security-group swap (including the tracked-connection caveat), role session revocation, access-key deactivation, IMDSv2 enforcement, user lockout, S3 Block Public Access, and logging restore. Each one captures evidence first and includes rollback. Nothing state-changing runs until you type CONFIRM <resource-id>.
Also included: a read-only IAM privilege-escalation module (13 known paths, simulate-principal-policy), plus triage card, ticket, and executive-summary templates. Five synthetic findings in examples/ let you exercise the skill without touching an account.
Works from pasted JSON with no AWS access, or live with AWS CLI v2. This listing is non-exclusive; the same pack remains available on Gumroad.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Security.
GuardDuty finding types change; verify unfamiliar types against the current AWS finding-types page. Athena needs a CloudTrail table in the account. The skill supports a responder and does not replace your organization's IR policy or legal notification duties. Five bundled findings are synthetic (RFC 5737 addresses, placeholder IDs).
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 6 days ago
Nothing to install. It runs in your AI agent.
- Optional
- AWS CLI v2
Permissions
Read-only by default: describe-*, get-*, list-*, lookup-events, simulate-principal-policy, and query APIs. State-changing AWS CLI from references/containment.md is allowed only after the user types CONFIRM <resource-id>. Never echo secrets or session tokens.