Install
$ agentstack add skill-mukul975-anthropic-cybersecurity-skills-analyzing-office365-audit-logs-for-compromise ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Analyzing Office 365 Audit Logs for Compromise
Overview
Business Email Compromise (BEC) attacks often leave traces in Office 365 audit logs: suspicious inbox rule creation, email forwarding to external addresses, mailbox delegation changes, and unauthorized OAuth application consent grants. This skill uses the Microsoft Graph API to query the Unified Audit Log, enumerate inbox rules across mailboxes, detect forwarding configurations, and identify compromised account indicators.
When to Use
- When investigating security incidents that require analyzing office365 audit logs for compromise
- When building detection rules or threat hunting queries for this domain
- When SOC analysts need structured procedures for this analysis type
- When validating security monitoring coverage for related attack techniques
Prerequisites
- Azure AD app registration with
AuditLog.Read.All,MailboxSettings.Read,Mail.Read(application permissions) - Python 3.9+ with
msal,requests - Client secret or certificate for authentication
- Global Reader or Security Reader role
Steps
- Authenticate to Microsoft Graph using MSAL client credentials flow
- Query Unified Audit Log for suspicious operations (Set-Mailbox, New-InboxRule)
- Enumerate inbox rules across mailboxes and flag forwarding rules
- Detect mailbox delegation changes (Add-MailboxPermission)
- Identify OAuth consent grants to suspicious applications
- Check for suspicious sign-in patterns from audit logs
- Generate compromise indicator report with timeline
Expected Output
- JSON report listing forwarding rules, delegation changes, OAuth grants, and suspicious audit events with risk scores
- Timeline of compromise indicators with affected mailboxes
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: mukul975
- Source: mukul975/Anthropic-Cybersecurity-Skills
- License: Apache-2.0
- Homepage: https://mahipal.engineer/Anthropic-Cybersecurity-Skills/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.