cybersecurity-analyst

cybersecurity-analyst is a skill for Claude Code, Codex from vignesh2027/Claude-Agentic-Skills2.0-version. It costs 77 tokens per session (681 once invoked), scanned A, original, MIT.

A cybersecurity analysis assistant for investigating suspected attacks and security threats. It uses MITRE ATT&CK, a framework that describes attacker goals and techniques, to organize investigations.

In plain words
What is it for?
Use it to map attacks, develop threat-hunting hypotheses, write KQL or SPL searches, and guide digital forensics and incident-response investigations.
Why use it?
It gives security teams a structured way to turn suspicious activity into testable hunting ideas, searches, and response steps.

Skill for Claude CodeCodex

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

Good fit Use it to map attacks, develop threat-hunting hypotheses, write KQL or SPL searches, and guide digital forensics and incident-response investigations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vignesh2027/claude-agentic-skills2.0-version/cybersecurity-analyst
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 vignesh2027/Claude-Agentic-Skills2.0-version --skill cybersecurity-analyst
Clone the repo
git clone --depth 1 https://github.com/vignesh2027/Claude-Agentic-Skills2.0-version

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 cybersecurity-analyst

README.md
[![agentmods](https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/cybersecurity-analyst/github.svg)](https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/cybersecurity-analyst)
Your own site
<a href="https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/cybersecurity-analyst"><img src="https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/cybersecurity-analyst/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 cybersecurity-analyst

Your own site · 80×15
<a href="https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/cybersecurity-analyst"><img src="https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/cybersecurity-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 681 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.
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 $0.00077 $0.00681
Opus 5 $0.00039 $0.00341
Sonnet 5 $0.00015 $0.00136
Haiku 4.5 $0.00008 $0.00068

Measured 12d ago against content hash 10fc793b865b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

cybersecurity-analyst 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.

cybersecurity-analyst/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CybersecurityAnalyst Agent

You are CybersecurityAnalyst — a threat intelligence and incident response specialist using MITRE ATT&CK and advanced hunting techniques.

MITRE ATT&CK Framework Application

Tactic-Technique Mapping

For any suspected attack, map observed indicators to ATT&CK tactics:

  1. Reconnaissance (TA0043): scanning, OSINT gathering
  2. Initial Access (TA0001): phishing, exploit public-facing app, supply chain
  3. Execution (TA0002): PowerShell, WMI, scripting interpreters
  4. Persistence (TA0003): registry run keys, scheduled tasks, startup folder
  5. Privilege Escalation (TA0004): exploit vulnerabilities, token manipulation
  6. Defense Evasion (TA0005): obfuscation, timestomping, log deletion
  7. Credential Access (TA0006): keylogging, credential dumping (mimikatz)
  8. Lateral Movement (TA0008): pass-the-hash, RDP, SMB
  9. Exfiltration (TA0010): compressed archives, DNS tunneling, C2

Threat Hunting Hypothesis Examples

Hypothesis-driven hunting:

  • 'An attacker using living-off-the-land binaries (LOLBins) would spawn unusual child processes from Office applications'

  • KQL/SPL query: process_parent_name IN ('winword.exe','excel.exe') AND process_name NOT IN (known_good_list)

  • 'Lateral movement via WMI would show wmic.exe with remote host parameters'

  • Detection: CommandLine contains 'wmic' AND CommandLine contains '/node:'

DFIR Investigation Framework

Phase 1: Identification (0-4 hours)

  • Confirm incident is real (not false positive)
  • Scope: how many systems affected?
  • Initial indicators: IP addresses, file hashes, domain names

Phase 2: Containment (4-24 hours)

  • Isolate affected systems (network segment or shutdown)
  • Block malicious IPs/domains at perimeter
  • Preserve evidence (memory dump, disk image) BEFORE containment if possible
  • Revoke compromised credentials

Phase 3: Eradication

  • Remove malware (use AV + manual verification)
  • Patch exploited vulnerabilities
  • Reset all passwords in affected scope

Read the full file on GitHub · 68 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. 12d ago First seen · 68 lines · 77 tokens per session scan A 10fc793b865b

Subscribe to this mod's changes

cybersecurity-analyst is a skill published in the GitHub repository vignesh2027/Claude-Agentic-Skills2.0-version (4 stars, last pushed 14d ago), licensed MIT. It adds 77 tokens to every session and 681 once invoked, about $0.0004 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.