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 EvilFreelancer/secs --skill investigating-m365-entragit clone --depth 1 https://github.com/EvilFreelancer/secsWrote 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/evilfreelancer/secs/investigating-m365-entra)<a href="https://agentmods.dev/skills/evilfreelancer/secs/investigating-m365-entra"><img src="https://agentmods.dev/badge/skills/evilfreelancer/secs/investigating-m365-entra/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/evilfreelancer/secs/investigating-m365-entra"><img src="https://agentmods.dev/badge/skills/evilfreelancer/secs/investigating-m365-entra.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00110 | $0.01560 |
| Opus 5 | $0.00055 | $0.00780 |
| Sonnet 5 | $0.00022 | $0.00312 |
| Haiku 4.5 | $0.00011 | $0.00156 |
Grade A, and why
investigating-m365-entra 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigating M365 / Entra Incidents
A Microsoft 365 compromise usually leaves no host to image — the crime scene is entirely in the cloud logs. An attacker who phishes a session token or tricks a user into consenting a malicious OAuth app does not need malware: they read mail, set a hidden forwarding rule, and pivot to invoice fraud, and every step is a record in the Unified Audit Log (UAL), the Entra sign-in logs, or the mailbox configuration. The investigator reconstructs the takeover from those records. The urgency is twofold: UAL retention is finite, and any forwarding or inbox rule the attacker set is still exfiltrating mail while you investigate.
Confirm the tenant is in scope per AGENTS.md. Enable/confirm UAL access early and export the relevant window before retention lapses. This is read-only investigation; disabling the account, revoking sessions, or removing a malicious app is the operator's containment call.
When to Use
- A suspected M365/Entra account takeover or business email compromise (BEC)
- No disk or memory to image — only cloud logs (UAL, sign-ins, OAuth grants)
- Hunting hidden inbox/forwarding rules and delegate/permission changes
- Investigating malicious OAuth app consent as a persistence and exfil path
- Reconstructing token/session theft that bypassed MFA
When NOT to Use
- Azure resource control plane (subscriptions, RBAC, Key Vault, VMs) — use
investigating-azure-incidents; this skill is the M365 workload and identity layer - AWS or GCP — use
investigating-aws-incidentsorinvestigating-gcp-incidents - On-host artifacts — use
investigating-windows-endpoints - Triaging the phishing email that started it — use
analyzing-phishing-emails - Proactive search with no incident yet — use
hunting-threats - Running the whole incident — use
responding-to-incidents - Packaging IOCs into a product — use
producing-threat-intelligence
Reconstruct from the Cloud Logs
Unified Audit Log is the backbone. Search it for the suspect user and window:
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.
- 12d ago First seen · 108 lines · 110 tokens per session scan A 509396db565e
investigating-m365-entra is a skill published in the GitHub repository EvilFreelancer/secs (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 110 tokens to every session and 1,560 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
Blue Team Defense & Hardening
System hardening, detection engineering, security baseline monitoring, patch management, defense-in-depth architecture, and security posture improvement.
analyzing-ransomware-encryption-mechanisms
Analyzes encryption algorithms, key management, and file encryption routines used by ransomware families to assess decryption feasibility, identify implementation weaknesses, and support recovery efforts. Covers AES, RSA, ChaCha20, and hybrid encryption schemes. Activates for requests involving ransomware…
analyzing-slack-space-and-file-system-artifacts
Examine file system slack space, MFT entries, USN journal, and alternate data streams to recover hidden data and reconstruct file activity on NTFS volumes.
conducting-mobile-app-penetration-test
Conducts penetration testing of iOS and Android mobile applications following the OWASP Mobile Application Security Testing Guide (MASTG) to identify vulnerabilities in data storage, network communication, authentication, cryptography, and platform-specific security controls. The tester performs static analysis of…
configuring-identity-aware-proxy-with-google-iap
Configuring Google Cloud Identity-Aware Proxy (IAP) to enforce per-request identity verification for Compute Engine, App Engine, Cloud Run, and GKE services using access levels, context-aware policies, and programmatic access with service accounts.
configuring-network-segmentation-with-vlans
Designs and implements VLAN-based network segmentation on managed switches to isolate network zones, enforce access control between segments, and reduce the attack surface by limiting lateral movement paths in enterprise network environments.