Agent skill

Implementing Soar Automation With Phantom

by mukul975 in mukul975/Anthropic-Cybersecurity-Skills

Implements Security Orchestration, Automation, and Response (SOAR) workflows using Splunk SOAR (formerly Phantom) to automate alert triage, IOC enrichment, containment actions, and incident response…

Apache-2.0Auto-check passedSecurity

Install Implementing Soar Automation With Phantom

skills CLI
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-soar-automation-with-phantom -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills implementing-soar-automation-with-phantom --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/implementing-soar-automation-with-phantom .claude/skills/implementing-soar-automation-with-phantom && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
implementing-soar-automation-with-phantom
GitHub stars
34k
Token cost
~3.6k tokens
SKILL.md length
440 words
Files
4 (incl. scripts, references)
Skills in repo
644
Repo updated
First seen
Licence
Apache-2.0

At a glance

Implements Security Orchestration, Automation, and Response (SOAR) workflows using Splunk SOAR (formerly Phantom) to automate alert triage, IOC enrichment, containment actions, and incident response…

  • Works in 6 steps: Configure Asset Connections → Build Phishing Triage Playbook → Build Alert Enrichment Playbook → …
  • SOC teams need to reduce manual analyst work
  • SKILL.md covers When to Use, Prerequisites, Workflow and Key Concepts, plus 3 more sections
  • Runs Python scripts from its folder; reaches api.crowdstrike.com; needs CS_CLIENT_SECRET and SERVICE_ACCOUNT_PASSWORD

What it does

Implementing Soar Automation With Phantom is an agent skill from mukul975/Anthropic-Cybersecurity-Skills. Implements Security Orchestration, Automation, and Response (SOAR) workflows using Splunk SOAR (formerly Phantom) to automate alert triage, IOC enrichment, containment actions, and incident response playbooks. Use when SOC teams need to reduce manual analyst work, standardize response procedures, or integrate multiple security tools into automated workflows.

Its SKILL.md is about 3.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts and reference files (for example `references/api-reference.md` and `scripts/agent.py`).

It sits in Security, covering Security operations and Incident response. It works with Splunk. The repository describes itself as: 817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io…. The licence is Apache-2.0.

When your agent uses it

  • SOC teams need to reduce manual analyst work
  • Standardize response procedures
  • Integrate multiple security tools into automated workflows

Example prompts

  • “Use the implementing-soar-automation-with-phantom skill to implement Security Orchestration, Automation, and Response (SOAR) workflows using Splunk…”
  • “/implementing-soar-automation-with-phantom”

Requirements

  • Python 3
  • A credential in YOUR_VT_API_KEY
  • A credential in CS_CLIENT_SECRET

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Configure Asset Connections
  2. Build Phishing Triage Playbook
  3. Build Alert Enrichment Playbook
  4. Implement Approval Gates for High-Impact Actions
  5. Configure Playbook Scheduling and Triggers
  6. Monitor Playbook Performance

What it can do on your machine

Read from SKILL.md and the folder at commit 54a7988. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • api.crowdstrike.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • CS_CLIENT_SECRET
    • SERVICE_ACCOUNT_PASSWORD

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Implementing Soar Automation With Phantom loads about 3.6k tokens when it runs, and up to ~4.3k if it reads all its reference files. Until then it costs about 101 tokens; SKILL.md has 440 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~101
When it runs · the whole SKILL.md, loaded when a task matches
~3.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from mukul975/Anthropic-Cybersecurity-Skills at commit 54a7988, republished under its Apache-2.0 licence (© mukul975). 440 words, ~3,643 tokens.

Download SKILL.mdSave it as .claude/skills/implementing-soar-automation-with-phantom/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
implementing-soar-automation-with-phantom
description
Implements Security Orchestration, Automation, and Response (SOAR) workflows using Splunk SOAR (formerly Phantom) to automate alert triage, IOC enrichment, containment actions, and incident response playbooks. Use when SOC teams need to reduce manual analyst work, standardize response procedures, or integrate multiple security tools into automated workflows.
domain
cybersecurity
subdomain
soc-operations
tags
soc, soar, phantom, splunk-soar, automation, playbook, orchestration, incident-response
mitre_attack
T1078, T1685.002, T1685.005, T1566
version
1.0
author
mahipal
license
Apache-2.0
nist_csf
DE.CM-01, DE.AE-02, RS.MA-01, DE.AE-06

Implementing SOAR Automation with Phantom

When to Use

Use this skill when:

  • SOC teams need to automate repetitive triage and enrichment tasks for high-volume alerts
  • Manual response times exceed SLA requirements and automation can reduce MTTR
  • Multiple security tools (SIEM, EDR, firewall, TIP) need orchestrated response actions
  • Playbook standardization is required to ensure consistent analyst response across shifts

Do not use for fully autonomous containment without human approval gates — always include analyst decision points for high-impact actions like account disabling or host isolation.

Prerequisites

  • Splunk SOAR (Phantom) 6.x+ deployed with web interface access
  • App connectors configured: VirusTotal, CrowdStrike, ServiceNow, Active Directory, Splunk ES
  • Splunk ES integration for ingesting notable events as SOAR events
  • API credentials for each integrated tool stored in SOAR asset configuration
  • Python knowledge for custom playbook actions

Workflow

Step 1: Configure Asset Connections

Set up integrations with security tools via SOAR Apps:

VirusTotal Asset Configuration:

json
{
  "app": "VirusTotal v3",
  "asset_name": "virustotal_prod",
  "configuration": {
    "api_key": "YOUR_VT_API_KEY",
    "rate_limit": true,
    "max_requests_per_minute": 4
  },
  "product_vendor": "VirusTotal",
  "product_name": "VirusTotal"
}

CrowdStrike Falcon Asset:

json
{
  "app": "CrowdStrike Falcon",
  "asset_name": "crowdstrike_prod",
  "configuration": {
    "client_id": "CS_CLIENT_ID",
    "client_secret": "CS_CLIENT_SECRET",
    "base_url": "https://api.crowdstrike.com"
  }
}

Active Directory Asset:

json
{
  "app": "Active Directory",
  "asset_name": "ad_prod",
  "configuration": {
    "server": "dc01.company.com",
    "username": "soar_service@company.com",
    "password": "SERVICE_ACCOUNT_PASSWORD",
    "ssl": true
  }
}
Step 2: Build Phishing Triage Playbook

Create an automated phishing response playbook in Python (Phantom playbook format):

python
"""
Phishing Triage Automation Playbook
Trigger: New phishing email reported via Splunk ES notable or email ingestion
"""

import phantom.rules as phantom
import json

def on_start(container):
    # Extract artifacts (URLs, file hashes, sender) from the container
    artifacts = phantom.get_artifacts(container_id=container["id"])

    for artifact in artifacts:
        artifact_type = artifact.get("cef", {}).get("type", "")

        if artifact_type == "url":
            phantom.act("url reputation", targets=artifact,
                        assets=["virustotal_prod"],
                        callback=url_reputation_callback,
                        name="url_reputation")

        elif artifact_type == "hash":
            phantom.act("file reputation", targets=artifact,
                        assets=["virustotal_prod"],
                        callback=hash_reputation_callback,
                        name="file_reputation")

        elif artifact_type == "ip":
            phantom.act("ip reputation", targets=artifact,
                        assets=["virustotal_prod"],
                        callback=ip_reputation_callback,
                        name="ip_reputation")

def url_reputation_callback(action, success, container, results, handle):
    if not success:
        phantom.comment(container, "URL reputation check failed")
        return

    for result in results:
        data = result.get("data", [{}])[0]
        malicious_count = data.get("summary", {}).get("malicious", 0)
        total_engines = data.get("summary", {}).get("total_engines", 0)

        if malicious_count > 5:
            # High confidence malicious — auto-block and escalate
            phantom.act("block url", targets=result,
                        assets=["palo_alto_prod"],
                        name="block_malicious_url")

            phantom.set_severity(container, "high")
            phantom.set_status(container, "open")
            phantom.comment(container,
                f"URL flagged by {malicious_count}/{total_engines} engines. "
                f"Blocked on firewall. Escalating to Tier 2.")

            # Create ServiceNow ticket
            phantom.act("create ticket", targets=container,
                        assets=["servicenow_prod"],
                        parameters=[{
                            "short_description": f"Phishing - Malicious URL detected",
                            "urgency": "2",
                            "impact": "2"
                        }],
                        name="create_incident_ticket")

        elif malicious_count > 0:
            # Medium confidence — request analyst review
            phantom.promote(container, template="Phishing Investigation")
            phantom.comment(container,
                f"URL flagged by {malicious_count}/{total_engines} engines. "
                f"Requires analyst review.")

        else:
            # Clean — close with comment
            phantom.set_status(container, "closed")
            phantom.comment(container,
                f"URL clean: 0/{total_engines} engines flagged. Auto-closed.")

def hash_reputation_callback(action, success, container, results, handle):
    if not success:
        return

    for result in results:
        data = result.get("data", [{}])[0]
        positives = data.get("summary", {}).get("positives", 0)

        if positives > 10:
            # Known malware — quarantine and block
            phantom.act("quarantine device", targets=result,
                        assets=["crowdstrike_prod"],
                        name="isolate_endpoint")
            phantom.set_severity(container, "high")

def ip_reputation_callback(action, success, container, results, handle):
    if not success:
        return

    for result in results:
        data = result.get("data", [{}])[0]
        malicious = data.get("summary", {}).get("malicious", 0)

        if malicious > 3:
            phantom.act("block ip", targets=result,
                        assets=["palo_alto_prod"],
                        name="block_malicious_ip")
Step 3: Build Alert Enrichment Playbook

Automate enrichment for all incoming SIEM alerts:

python
"""
Universal Alert Enrichment Playbook
Runs on every new event to add context before analyst review
"""

import phantom.rules as phantom

def on_start(container):
    # Get all artifacts
    success, message, artifacts = phantom.get_artifacts(
        container_id=container["id"], full_data=True
    )

    ip_artifacts = [a for a in artifacts if a.get("cef", {}).get("sourceAddress")]
    domain_artifacts = [a for a in artifacts if a.get("cef", {}).get("destinationDnsDomain")]

    # Enrich IPs in parallel
    for artifact in ip_artifacts:
        ip = artifact["cef"]["sourceAddress"]

        # VirusTotal lookup
        phantom.act("ip reputation",
                    parameters=[{"ip": ip}],
                    assets=["virustotal_prod"],
                    callback=enrich_ip_callback,
                    name=f"vt_ip_{ip}")

        # GeoIP lookup
        phantom.act("geolocate ip",
                    parameters=[{"ip": ip}],
                    assets=["maxmind_prod"],
                    callback=geoip_callback,
                    name=f"geo_{ip}")

        # Whois lookup
        phantom.act("whois ip",
                    parameters=[{"ip": ip}],
                    assets=["whois_prod"],
                    name=f"whois_{ip}")

    # Enrich domains
    for artifact in domain_artifacts:
        domain = artifact["cef"]["destinationDnsDomain"]
        phantom.act("domain reputation",
                    parameters=[{"domain": domain}],
                    assets=["virustotal_prod"],
                    name=f"vt_domain_{domain}")

def enrich_ip_callback(action, success, container, results, handle):
    """Update container with enrichment data"""
    if success:
        for result in results:
            summary = result.get("summary", {})
            phantom.add_artifact(container, {
                "cef": {
                    "vt_malicious": summary.get("malicious", 0),
                    "vt_suspicious": summary.get("suspicious", 0),
                    "enrichment_source": "VirusTotal"
                },
                "label": "enrichment",
                "name": "VT IP Enrichment"
            })
Step 4: Implement Approval Gates for High-Impact Actions

Add human-in-the-loop for critical actions:

python
def containment_decision(action, success, container, results, handle):
    """Present analyst with containment options"""
    phantom.prompt(
        container=container,
        user="soc_tier2",
        message=(
            "Confirmed malicious activity detected.\n"
            f"Host: {container['artifacts'][0]['cef'].get('sourceAddress')}\n"
            f"Threat: {results[0]['summary'].get('threat_name')}\n\n"
            "Select containment action:"
        ),
        respond_in_mins=15,
        options=["Isolate Host", "Disable Account", "Both", "Monitor Only"],
        callback=execute_containment
    )

def execute_containment(action, success, container, results, handle):
    response = results.get("response", "Monitor Only")

    if response in ["Isolate Host", "Both"]:
        phantom.act("quarantine device",
                    parameters=[{"hostname": container["artifacts"][0]["cef"]["sourceHostName"]}],
                    assets=["crowdstrike_prod"],
                    name="isolate_host")

    if response in ["Disable Account", "Both"]:
        phantom.act("disable user",
                    parameters=[{"username": container["artifacts"][0]["cef"]["sourceUserName"]}],
                    assets=["ad_prod"],
                    name="disable_account")

    phantom.comment(container, f"Analyst approved: {response}")
Step 5: Configure Playbook Scheduling and Triggers

Set up event triggers in SOAR:

json
{
  "playbook_name": "phishing_triage_automation",
  "trigger": {
    "type": "event_created",
    "conditions": {
      "label": ["phishing", "notable"],
      "severity": ["high", "medium"]
    }
  },
  "active": true,
  "run_as": "automation_user"
}
Step 6: Monitor Playbook Performance

Track automation effectiveness with SOAR metrics:

python
# Query SOAR API for playbook execution stats
import requests

headers = {"ph-auth-token": "YOUR_SOAR_TOKEN"}
response = requests.get(
    "https://soar.company.com/rest/playbook_run",
    headers=headers,
    params={
        "page_size": 100,
        "filter": '{"status":"success"}',
        "sort": "create_time",
        "order": "desc"
    }
)
runs = response.json()["data"]

# Calculate automation metrics
total_runs = len(runs)
avg_duration = sum(r["end_time"] - r["start_time"] for r in runs) / total_runs
auto_closed = sum(1 for r in runs if r.get("auto_resolved"))
print(f"Total runs: {total_runs}")
print(f"Avg duration: {avg_duration:.1f}s")
print(f"Auto-resolved: {auto_closed}/{total_runs} ({auto_closed/total_runs*100:.0f}%)")

Key Concepts

TermDefinition
SOARSecurity Orchestration, Automation, and Response — platform integrating security tools with automated playbooks
PlaybookAutomated workflow defining sequential and parallel actions triggered by security events
AssetSOAR configuration for a connected security tool (API endpoint, credentials, connection parameters)
ContainerSOAR event object containing artifacts (IOCs) from an ingested alert or incident
ArtifactIndividual IOC or data point within a container (IP, hash, URL, domain, email)
Approval GateHuman-in-the-loop step requiring analyst decision before executing high-impact automated actions
Show full SKILL.md (138 more words)Show less

Tools & Systems

  • Splunk SOAR (Phantom): Enterprise SOAR platform with 300+ app integrations and visual playbook editor
  • Splunk ES: SIEM platform feeding notable events into SOAR as containers for automated triage
  • CrowdStrike Falcon: EDR platform integrated via SOAR for automated host isolation and threat hunting
  • ServiceNow: ITSM platform integrated for automated incident ticket creation and tracking
  • Palo Alto NGFW: Firewall integrated for automated IP/URL blocking via SOAR playbooks

Common Scenarios

  • Phishing Triage: Auto-extract URLs/attachments, detonate in sandbox, block malicious, create ticket
  • Malware Alert Enrichment: Auto-enrich file hashes across VT/MalwareBazaar, isolate if confirmed malicious
  • Brute Force Response: Auto-check if attack succeeded, disable account if compromised, block source IP
  • Threat Intel IOC Processing: Auto-ingest TI feed IOCs, check against internal logs, create blocks for matches
  • Vulnerability Alert Response: Auto-query asset database for affected systems, create patching ticket with priority

Output Format

SOAR PLAYBOOK EXECUTION REPORT
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Playbook:     Phishing Triage Automation v2.3
Container:    SOAR-2024-08921
Trigger:      Notable event from Splunk ES (phishing)

Actions Executed:
  [1] URL Reputation (VirusTotal)     — 14/90 engines malicious    [2.1s]
  [2] IP Reputation (AbuseIPDB)       — Confidence: 85%            [1.3s]
  [3] Block URL (Palo Alto)           — Blocked on PA-5260         [0.8s]
  [4] Block IP (Palo Alto)            — Blocked on PA-5260         [0.7s]
  [5] Create Ticket (ServiceNow)      — INC0012345 created         [1.5s]
  [6] Prompt Analyst (Tier 2)         — Response: "Isolate Host"   [4m 12s]
  [7] Quarantine Device (CrowdStrike) — WORKSTATION-042 isolated   [3.2s]

Total Duration:    4m 22s (vs 35min avg manual triage)
Time Saved:        ~31 minutes
Disposition:       True Positive — Escalated to IR

© mukul975, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts, references) in skills/implementing-soar-automation-with-phantom of mukul975/Anthropic-Cybersecurity-Skills.

  • SKILL.md
  • LICENSE
  • references/api-reference.md
  • scripts/agent.py

Open the folder on GitHubat commit 54a7988

Compare with similar skills

Implementing Soar Automation With Phantom next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Implementing Soar Automation With Phantom compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Implementing Soar Automation With Phantom this skillmukul975/Anthropic-Cybersecurity-Skills34k—~3.6kAutomated safety check: PassApache-2.0
Incident Triagebriiirussell/cybersecurity-skills413—~1.5kAutomated safety check: NotesMIT
Doca ArgusNVIDIA/skills3.5k—~4.8kAutomated safety check: PassApache-2.0
Breach Detection Systemmukul975/Privacy-Data-Protection-Skills297—~3kAutomated safety check: PassApache-2.0
Sentinelvinayaklatthe/microsoft-security-skills175—~2.2kAutomated safety check: PassMIT
Msp HelpdeskRTFM-IT-Services-LLC/msp-claude-skills115—~3.3kAutomated safety check: PassCustom licence

Similar skills

  • Incident Triage

    briiirussell/cybersecurity-skills

    Guide rapid triage and initial response to security incidents following NIST SP 800-61 methodology.

    413 GitHub stars~1.5k tokensUpdated 4 mo ago
    SecurityAuto-check: notes
  • Doca Argus

    NVIDIA/skills

    Official

    A skill your agent uses when the user is deploying or operating the DOCA Argus Service — the packaged BlueField-side runtime-security container that watches the BlueField and attached host for…

    3.5k GitHub stars~4.8k tokensUpdated today
    SecurityAuto-check passed
  • Breach Detection System

    mukul975/Privacy-Data-Protection-Skills

    Implements technical breach detection capabilities including SIEM integration, DLP alert configuration, anomaly detection rules, and insider threat monitoring.

    297 GitHub stars~3k tokensUpdated 6 mo ago
    SecurityAuto-check passed
  • Sentinel

    vinayaklatthe/microsoft-security-skills

    Guidance for designing and operating Microsoft Sentinel, the cloud-native SIEM and SOAR delivered through the Defender portal.

    175 GitHub stars~2.2k tokensUpdated 3 mo ago
    SecurityAuto-check passed
  • Msp Helpdesk

    RTFM-IT-Services-LLC/msp-claude-skills

    A skill your agent uses for anything about how your MSP runs day-to-day support: setting or questioning a ticket's priority, response and resolution targets, "the client says everything is down"…

    115 GitHub stars~3.3k tokensUpdated 7 days ago
    SecurityAuto-check passed
  • Detection Sigma

    AgentSecOps/SecOpsAgentKit

    Generic detection rule creation and management using Sigma, the universal SIEM rule format.

    220 GitHub starsUsed in 1 repo~4k tokens
    SecurityAuto-check passed

More from mukul975/Anthropic-Cybersecurity-Skills

All 644 skills in this repo
  • Campaign Attribution Evidence Analysis

    mukul975/Anthropic-Cybersecurity-Skills

    Weighs infrastructure, TTP, malware code and timing evidence with the Diamond Model and competing hypotheses to reach a confidence-rated attribution.

    34k GitHub stars~2.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Go Malware Analysis in Ghidra

    mukul975/Anthropic-Cybersecurity-Skills

    Walks through reverse engineering Go-compiled malware in Ghidra: parsing buildinfo and pclntab, recovering stripped function names and extracting dependencies.

    34k GitHub stars~2.8k tokensUpdated 1 mo ago
    Auto-check passed
  • LNK and Jump List Forensics

    mukul975/Anthropic-Cybersecurity-Skills

    Guides forensic analysis of Windows LNK shortcut files and Jump Lists with LECmd, JLECmd and manual parsing to show file access and program execution.

    34k GitHub stars~2.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Malware Persistence Analysis with Autoruns

    mukul975/Anthropic-Cybersecurity-Skills

    Hunts Windows malware persistence with Sysinternals Autoruns, covering run keys, services, scheduled tasks and drivers, with baseline comparison.

    34k GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed
  • NTFS MFT Deleted File Recovery

    mukul975/Anthropic-Cybersecurity-Skills

    Guides a Windows forensic examination of the NTFS Master File Table to recover deleted-file evidence, build timelines and spot timestomping.

    34k GitHub stars~2.7k tokensUpdated 1 mo ago
    Auto-check passed
  • Network Covert Channel Analysis

    mukul975/Anthropic-Cybersecurity-Skills

    Detects DNS tunneling, ICMP exfiltration and HTTP-based covert channels in packet captures and DNS logs when hunting for hidden command-and-control traffic.

    34k GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Questions about Implementing Soar Automation With Phantom

What does Implementing Soar Automation With Phantom do?

Implements Security Orchestration, Automation, and Response (SOAR) workflows using Splunk SOAR (formerly Phantom) to automate alert triage, IOC enrichment, containment actions, and incident response…. Implementing Soar Automation With Phantom is an agent skill from mukul975/Anthropic-Cybersecurity-Skills. Implements Security Orchestration, Automation, and Response (SOAR) workflows using Splunk SOAR (formerly Phantom) to automate alert triage, IOC enrichment, containment actions, and incident response playbooks.

When should I use Implementing Soar Automation With Phantom?

Implementing Soar Automation With Phantom fits situations like: SOC teams need to reduce manual analyst work; standardize response procedures; integrate multiple security tools into automated workflows.

How do I install Implementing Soar Automation With Phantom in Claude Code?

Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-soar-automation-with-phantom -a claude-code`. Or copy the skill folder (skills/implementing-soar-automation-with-phantom in mukul975/Anthropic-Cybersecurity-Skills) into .claude/skills/implementing-soar-automation-with-phantom in your project. Claude Code loads it when a task matches its description.

How do I install Implementing Soar Automation With Phantom in Codex?

Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-soar-automation-with-phantom -a codex`. Or copy the skill folder (skills/implementing-soar-automation-with-phantom in mukul975/Anthropic-Cybersecurity-Skills) into .agents/skills/implementing-soar-automation-with-phantom in your project. Codex loads it when a task matches its description.

Can I use Implementing Soar Automation With Phantom in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-soar-automation-with-phantom -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/implementing-soar-automation-with-phantom, .gemini/skills/implementing-soar-automation-with-phantom, .github/skills/implementing-soar-automation-with-phantom and .opencode/skills/implementing-soar-automation-with-phantom in your project.

What does Implementing Soar Automation With Phantom need to run?

Going by SKILL.md and its folder, Implementing Soar Automation With Phantom needs Python for the scripts in its folder and credentials named CS_CLIENT_SECRET and SERVICE_ACCOUNT_PASSWORD. Our summary lists: Python 3; A credential in YOUR_VT_API_KEY; A credential in CS_CLIENT_SECRET.

Does Implementing Soar Automation With Phantom access the network?

SKILL.md names 1 domain. In commands or code: api.crowdstrike.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Implementing Soar Automation With Phantom safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Implementing Soar Automation With Phantom use?

Implementing Soar Automation With Phantom is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Implementing Soar Automation With Phantom use?

About 3.6k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 655 tokens, read only when the agent opens those files.

What are the alternatives to Implementing Soar Automation With Phantom?

Skills that share tags, products or a category with Implementing Soar Automation With Phantom: Incident Triage (briiirussell/cybersecurity-skills, 413 stars), Doca Argus (NVIDIA/skills, 3.5k stars), Breach Detection System (mukul975/Privacy-Data-Protection-Skills, 297 stars) and Sentinel (vinayaklatthe/microsoft-security-skills, 175 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Implementing Soar Automation With Phantom?

mukul975 (a GitHub user) maintains it in mukul975/Anthropic-Cybersecurity-Skills, which has 33,993 GitHub stars. The repository holds 644 skills in this directory. The repository was last updated on August 31, 2026.

Source: mukul975/Anthropic-Cybersecurity-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.