More screenshots
Works with the AI Agents you already use
windows event log security analyzer
Analyze exported Windows Security/System/PowerShell XML or CSV for sprays, break-ins, new services and ATT&CK-mapped findings. Not .evtx.
$20
windows event log security analyzer
Example session with this skill installed
I exported Security and System logs from DC01 after a weird weekend. Was there a spray? Did anyone get in? Anything persistence-y?
- Read your context and instructions
- Compiled the windows event log
Answer: yes — 2 CRITICAL, 6 HIGH.
- CRITICAL: Successful RDP logon by Administrator from 203.0.113.77 after 15 failures (T1078)
- CRITICAL: Security audit log cleared by Administrator (T1070.001)
- HIGH: Password spray from 203.0.113.50 — 10 users / 30 min (T1110.003)
- HIGH: Password guessing against Administrator (T1110.001)
- HIGH: Account
backupsvccreated and added to Administrators (T1136.001 / T1098) - HIGH: Service
WinUpdateHelper→C:\Users\Public\update.bat(T1543.003) - HIGH: PowerShell
IEX (New-Object Net.WebClient).DownloadString(...)(T1059.001)
Deliverables: summary, hunt.md, timeline CSV, JSON. Input: 34 events, span 20 minutes.
(Real run on bundled synthetic XML; IPs are RFC 5737 documentation addresses.)
Connects securely to your tools. The creator never sees your data.
About this skill
Hunt Windows logs you already exported — without a SIEM.
Reads wevtutil / Get-WinEvent XML or CSV (native .evtx is refused with a clear error). Detects password sprays (4625), interesting 4624 logon types, success-after-failures, account/group changes (4720/4732/…), audit log clears (1102), new services (7045/4697), suspicious PowerShell 4104, scheduled tasks (4698) and explicit credentials (4648). Every finding carries a MITRE ATT&CK ID.
What's included
SKILL.md (export commands + safety rules), scripts/winlog.py, synthetic incident XML, references.
- Signature/threshold based — quiet valid-credential abuse can look normal.
- Native
.evtxunsupported by design (export first). - Needs timestamps in the export for spray windows; without them, falls back to totals.
- Does not query Domain Controllers or contact source IPs.
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 any payment.
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 1 month ago
Permissions
File Scopes
Fully offline. Scripts never import networking or subprocess modules and never modify system or cloud configuration.