Anthropic Cybersecurity Skills is a library of structured cybersecurity procedures for AI agents, covering security domains and mappings to established security frameworks. It is for authorized security analysis, penetration testing, incident response, research, defense, and education across compatible AI platforms. The catalogue entries package parts of this library as agent skills, instructions, or a plugin.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill analyzing-office365-audit-logs-for-compromisegit clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-SkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mukul975/anthropic-cybersecurity-skills/analyzing-office365-audit-logs-for-compromise)<a href="https://agentmods.dev/skills/mukul975/anthropic-cybersecurity-skills/analyzing-office365-audit-logs-for-compromise"><img src="https://agentmods.dev/badge/skills/mukul975/anthropic-cybersecurity-skills/analyzing-office365-audit-logs-for-compromise/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mukul975/anthropic-cybersecurity-skills/analyzing-office365-audit-logs-for-compromise"><img src="https://agentmods.dev/badge/skills/mukul975/anthropic-cybersecurity-skills/analyzing-office365-audit-logs-for-compromise.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.00511 |
| Opus 5 | $0.00023 | $0.00255 |
| Sonnet 5 | $0.00009 | $0.00102 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
analyzing-office365-audit-logs-for-compromise scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
5 near-identical copies found in the catalogue:
- analyzing-office365-audit-logs-for-compromise — 100% identical, 0 lines differ
- analyzing-office365-audit-logs-for-compromise — 100% identical, 0 lines differ
- analyzing-office365-audit-logs-for-compromise — 97% identical, 10 lines differ
- analyzing-office365-audit-logs-for-compromise — 88% identical, 25 lines differ
- analyzing-office365-audit-logs-for-compromise — 88% identical, 25 lines differ
What it actually says
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
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 13d ago First seen · 66 lines · 46 tokens per session scan A 9e9561397e5e
analyzing-office365-audit-logs-for-compromise is a skill published in the GitHub repository mukul975/Anthropic-Cybersecurity-Skills (32,631 stars, last pushed 12d ago), licensed Apache-2.0. It adds 46 tokens to every session and 511 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
analyzing-office365-audit-logs-for-compromise
Parse Office 365 Unified Audit Logs via Microsoft Graph API to detect email forwarding rule creation, inbox delegation, suspicious OAuth app grants, and other indicators of account compromise.
analyzing-office365-audit-logs-for-compromise
Parse Office 365 Unified Audit Logs via Microsoft Graph API to detect email forwarding rule creation, inbox delegation, suspicious OAuth app grants, and other indicators of account compromise.
analyzing-office365-audit-logs-for-compromise
Parse Office 365 Unified Audit Logs via Microsoft Graph API to detect email forwarding rule creation, inbox delegation, suspicious OAuth app grants, and other indicators of account compromise.
analyzing-office365-audit-logs-for-compromise
A guide to examining Microsoft 365 audit records through Microsoft Graph, Microsoft's API for accessing service data, to find signs that an account was taken over.
analyzing-office365-audit-logs-for-compromise
Parse Office 365 Unified Audit Logs via Microsoft Graph API to detect email forwarding rule creation, inbox delegation, suspicious OAuth app grants, and other indicators of account compromise.
analyzing-office365-audit-logs-for-compromise
Parse Office 365 Unified Audit Logs via Microsoft Graph API to detect email forwarding rule creation, inbox delegation, suspicious OAuth app grants, and other indicators of account compromise.