security-investigator: Skill for Claude Code

.github/skills/scope-drift-detection/spn/SKILL.md

scope-drift-detection-spn is a skill for Claude Code, Codex from SCStelz/security-investigator. It costs 127 tokens per session (9,392 once invoked), scanned A, original, MIT.

A guide for finding gradual changes in the behavior and access of Entra ID service principals, which are identities used by applications and automation. It compares recent activity with a 90-day baseline to identify unusual expansion.

In plain words
What is it for?
Use it to check automation accounts, app registrations, and managed identities for unusual sign-in volumes, new resources, source IP addresses, or geographic locations.
Why use it?
Slow increases in access or activity can avoid alerts designed for sudden attacks; comparing behavior with its normal baseline helps expose these changes.

Skill for Claude CodeCodex

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

This is SCStelz/security-investigator's own configuration. It tells Claude Code and Codex how to work on security-investigator itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything security-investigator configures →

Reuse

Borrowing it

Nothing to install: this file belongs to SCStelz/security-investigator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/SCStelz/security-investigator/main/.github/skills/scope-drift-detection/spn/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/SCStelz/security-investigator

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 scope-drift-detection-spn

README.md
[![agentmods](https://agentmods.dev/badge/skills/scstelz/security-investigator/spn/github.svg)](https://agentmods.dev/skills/scstelz/security-investigator/spn)
Your own site
<a href="https://agentmods.dev/skills/scstelz/security-investigator/spn"><img src="https://agentmods.dev/badge/skills/scstelz/security-investigator/spn/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 scope-drift-detection-spn

Your own site · 80×15
<a href="https://agentmods.dev/skills/scstelz/security-investigator/spn"><img src="https://agentmods.dev/badge/skills/scstelz/security-investigator/spn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,392 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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: 2 findings, up to medium

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 →

  • medium Excessive Agency · line 104
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Agent Snooping · line 715
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 $0.00127 $0.09392
Opus 5 $0.00063 $0.04696
Sonnet 5 $0.00025 $0.01878
Haiku 4.5 $0.00013 $0.00939

Measured 10d ago against content hash b078a5d36495, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

scope-drift-detection-spn 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 10d 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.

.github/skills/scope-drift-detection/spn/SKILL.md · 721 lines

How it starts

The opening of the file, as written. The whole thing — 721 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Service Principal Scope Drift Detection — Instructions

Purpose

Credit: The scope drift detection concept for service principals was inspired by Iftekhar Hussain's article The Agentic SOC Era: How Sentinel MCP Enables Autonomous Security Reasoning (Feb 2026), which demonstrated multi-source correlation across AADServicePrincipalSignInLogs, AuditLogs, and SecurityAlert to build 90-day behavioral baselines and surface drift via weighted scoring.

This skill detects scope drift — the gradual, often imperceptible expansion of access or behavior beyond an established baseline — in Entra ID service principals. Unlike sudden compromise (which triggers alerts), scope drift is a slow-burn pattern that evades threshold-based detections.

Entity Type: Service Principal

Identifier Primary Table(s) Use Case
ServicePrincipalName / ServicePrincipalId AADServicePrincipalSignInLogs App registrations, automation accounts, managed identities

What this skill detects:

  • Volume spikes in sign-in activity relative to historical baseline
  • New target resources (APIs, services) not previously accessed
  • New source IP addresses or geographic locations
  • Increased failure rates indicating probing or misconfiguration
  • Credential/permission changes correlated with behavioral shifts
  • Security alerts involving the drifting entities

Related skills:


📑 TABLE OF CONTENTS

  1. Critical Workflow Rules - Start here!
  2. Output Modes - Inline chat vs. Markdown file
  3. Quick Start - 7-step investigation pattern
  4. Drift Score Formula - Weighted composite scoring (5 dimensions)
  5. Execution Workflow - Complete 4-phase process
  6. Sample KQL Queries - Validated query patterns (Queries 1-4)
  7. Report Template - Output format specification
  8. Known Pitfalls - Edge cases and false positives
  9. Error Handling - Troubleshooting guide
  10. SVG Dashboard Generation - Visual dashboard from report

Read the full file on GitHub · 721 lines

Files

What ships with it

1 file 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.

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. 10d ago First seen · 721 lines · 127 tokens per session scan A b078a5d36495

Subscribe to this mod's changes

scope-drift-detection-spn is a skill published in the GitHub repository SCStelz/security-investigator (245 stars, last pushed 2d ago), licensed MIT. It adds 127 tokens to every session and 9,392 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens