security-investigator: Skill for Claude Code

.github/skills/data-security-analysis/SKILL.md

data-security-analysis is a skill for Claude Code, Codex from SCStelz/security-investigator. It costs 179 tokens per session (21,445 once invoked), scanned A, original, MIT.

A guide for analyzing Microsoft Purview data-security events, which record activity involving sensitive information and protected documents. It covers sensitive information types such as credit-card numbers, sensitivity labels, data-loss-prevention matches, and insider-risk activity.

In plain words
What is it for?
Use it to audit access to sensitive or labeled documents, review DLP events, monitor exact-data matches, find users with risky data activity, and track label changes.
Why use it?
It helps identify who accessed sensitive data, what policies matched, and whether labels were changed or downgraded.

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/data-security-analysis/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 data-security-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/scstelz/security-investigator/data-security-analysis.svg)](https://agentmods.dev/skills/scstelz/security-investigator/data-security-analysis)
Your own site
<a href="https://agentmods.dev/skills/scstelz/security-investigator/data-security-analysis"><img src="https://agentmods.dev/badge/skills/scstelz/security-investigator/data-security-analysis.svg" alt="Measured on agentmods" height="20"></a>
Per session 179 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 21,445 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 System Prompt Leakage · line 1038
    Skill contains patterns that could indirectly extract system prompts through rephrasing, translation, summarization, or side-channel techniques.
    Fix: Guard against indirect extraction by refusing to summarize, translate, or rephrase system instructions. Add explicit anti-extraction clauses.
  • medium Agent Snooping · line 1432
    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 $0.00179 $0.21445
Opus 5 $0.00089 $0.10722
Sonnet 5 $0.00036 $0.04289
Haiku 4.5 $0.00018 $0.02144

Measured 8d ago against content hash a8cce9c2a058, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

data-security-analysis 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 8d 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/data-security-analysis/SKILL.md · 1,437 lines

How it starts

The opening of the file, as written. The whole thing — 1,437 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Security Events Analysis — Instructions

Purpose

This skill analyzes DataSecurityEvents (Microsoft Purview Insider Risk Management / DLP telemetry) to answer questions about who accessed documents containing sensitive information types (SITs) and/or sensitivity labels — including EDM (Exact Data Match), built-in SITs (credit cards, SSNs, etc.), trainable classifiers, and Microsoft Purview sensitivity labels (Confidential, Highly Confidential, custom labels, etc.).

Primary Table: DataSecurityEvents (Defender XDR Advanced Hunting)

Use Case Example Question
SIT access audit "Who accessed files with credit card numbers in the last 30 days?"
EDM monitoring "Show me all access to documents matching our EDM SIT"
DLP event analysis "What DLP policy matches occurred this week?"
Insider risk triage "Which users have the most sensitive data interactions?"
SIT landscape overview "What sensitive information types exist in our environment?"
Sensitivity label audit "Who accessed Highly Confidential labeled documents?"
Label change tracking "Show me all label downgrades in the last 30 days"
Copilot label exposure "What labeled documents did Copilot access in risky interactions?"

📑 TABLE OF CONTENTS

  1. Critical Workflow Rules - Start here!
  2. SIT GUID Mapping Strategy - How SIT GUIDs are resolved to names
  3. Label GUID Mapping Strategy - How sensitivity label GUIDs are resolved to names
  4. Output Modes - Inline chat vs. Markdown file
  5. Quick Start - 8-step execution pattern
  6. Execution Workflow - 6-phase analysis process
  7. Sample KQL Queries - Validated query patterns (Queries 1-16d)
  8. Report Template - Rendering rules (15 rules) + output format specification
  9. Known Pitfalls - Table quirks and edge cases (27 entries)
  10. Error Handling - Troubleshooting guide
  11. SVG Dashboard Generation - Visual dashboard from report data

Read the full file on GitHub · 1,437 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. 8d ago First seen · 1,437 lines · 179 tokens per session scan A a8cce9c2a058

Subscribe to this mod's changes

data-security-analysis is a skill published in the GitHub repository SCStelz/security-investigator (244 stars, last pushed 2d ago), licensed MIT. It adds 179 tokens to every session and 21,445 once invoked, about $0.0009 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

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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens