Frontmcp Authorities
agentfront/frontmcp
A skill your agent uses when implementing authorization and access control for FrontMCP tools, resources, prompts, or skills, deciding who may invoke what.
Agent skill
Implements device posture assessment as a zero trust access control by integrating endpoint health signals from CrowdStrike ZTA, Microsoft Intune, and Jamf into conditional access policies that…
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-device-posture-assessment-in-zero-trust -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills implementing-device-posture-assessment-in-zero-trust --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/implementing-device-posture-assessment-in-zero-trust .claude/skills/implementing-device-posture-assessment-in-zero-trust && rm -rf skills-srcUse ~/.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/
Install the "implementing-device-posture-assessment-in-zero-trust" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-device-posture-assessment-in-zero-trust into .claude/skills/implementing-device-posture-assessment-in-zero-trust/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-device-posture-assessment-in-zero-trust", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-device-posture-assessment-in-zero-trustType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-device-posture-assessment-in-zero-trust -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills implementing-device-posture-assessment-in-zero-trust --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/implementing-device-posture-assessment-in-zero-trust .agents/skills/implementing-device-posture-assessment-in-zero-trust && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "implementing-device-posture-assessment-in-zero-trust" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-device-posture-assessment-in-zero-trust into .agents/skills/implementing-device-posture-assessment-in-zero-trust/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-device-posture-assessment-in-zero-trust", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-device-posture-assessment-in-zero-trust -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills implementing-device-posture-assessment-in-zero-trust --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/implementing-device-posture-assessment-in-zero-trust .cursor/skills/implementing-device-posture-assessment-in-zero-trust && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "implementing-device-posture-assessment-in-zero-trust" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-device-posture-assessment-in-zero-trust into .cursor/skills/implementing-device-posture-assessment-in-zero-trust/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-device-posture-assessment-in-zero-trust", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git --path skills/implementing-device-posture-assessment-in-zero-trust--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-device-posture-assessment-in-zero-trust -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills implementing-device-posture-assessment-in-zero-trust --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/implementing-device-posture-assessment-in-zero-trust .gemini/skills/implementing-device-posture-assessment-in-zero-trust && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "implementing-device-posture-assessment-in-zero-trust" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-device-posture-assessment-in-zero-trust into .gemini/skills/implementing-device-posture-assessment-in-zero-trust/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-device-posture-assessment-in-zero-trust", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills implementing-device-posture-assessment-in-zero-trustInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-device-posture-assessment-in-zero-trust -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/implementing-device-posture-assessment-in-zero-trust .github/skills/implementing-device-posture-assessment-in-zero-trust && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "implementing-device-posture-assessment-in-zero-trust" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-device-posture-assessment-in-zero-trust into .github/skills/implementing-device-posture-assessment-in-zero-trust/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-device-posture-assessment-in-zero-trust", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-device-posture-assessment-in-zero-trust -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills implementing-device-posture-assessment-in-zero-trust --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/implementing-device-posture-assessment-in-zero-trust .opencode/skills/implementing-device-posture-assessment-in-zero-trust && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "implementing-device-posture-assessment-in-zero-trust" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-device-posture-assessment-in-zero-trust into .opencode/skills/implementing-device-posture-assessment-in-zero-trust/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-device-posture-assessment-in-zero-trust", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
implementing-device-posture-assessment-in-zero-trustImplements device posture assessment as a zero trust access control by integrating endpoint health signals from CrowdStrike ZTA, Microsoft Intune, and Jamf into conditional access policies that…
Implementing Device Posture Assessment In Zero Trust is an agent skill from mukul975/Anthropic-Cybersecurity-Skills. Implements device posture assessment as a zero trust access control by integrating endpoint health signals from CrowdStrike ZTA, Microsoft Intune, and Jamf into conditional access policies that enforce compliance before granting access. Use when requiring device health checks before app access, wiring posture signals into conditional access, or implementing the CISA Zero Trust device pillar.
Its SKILL.md is about 4.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including scripts, reference files and assets (for example `assets/template.md`, `references/api-reference.md` and `references/standards.md`).
It sits in Backend & APIs, covering Authorization and RBAC. It works with Okta. 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.
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 54a7988. It shows what the files ask for, not the result of running them.
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.
Ships 2 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
curlFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
api.crowdstrike.comgraph.microsoft.comFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
CS_TOKENOKTA_API_TOKENJAMF_TOKENFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Implementing Device Posture Assessment In Zero Trust loads about 4.1k tokens when it runs, and up to ~5.9k if it reads all its reference files. Until then it costs about 112 tokens; SKILL.md has 655 words of instructions outside code blocks.
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.
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.
The full file from mukul975/Anthropic-Cybersecurity-Skills at commit 54a7988, republished under its Apache-2.0 licence (© mukul975). 655 words, ~4,107 tokens.
.claude/skills/implementing-device-posture-assessment-in-zero-trust/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.Do not use for IoT or headless devices that cannot run posture agents, as a standalone security control without identity verification, or when real-time posture data is unavailable and stale compliance data would create false trust.
Establish minimum security requirements for each device category.
# Microsoft Intune: Create device compliance policy via Graph API
Connect-MgGraph -Scopes "DeviceManagementConfiguration.ReadWrite.All"
# Windows 10/11 Compliance Policy
$compliancePolicy = @{
"@odata.type" = "#microsoft.graph.windows10CompliancePolicy"
displayName = "Zero Trust - Windows Compliance"
description = "Minimum device requirements for zero trust access"
osMinimumVersion = "10.0.19045"
bitLockerEnabled = $true
secureBootEnabled = $true
codeIntegrityEnabled = $true
tpmRequired = $true
antivirusRequired = $true
antiSpywareRequired = $true
defenderEnabled = $true
firewallEnabled = $true
passwordRequired = $true
passwordMinimumLength = 12
passwordRequiredType = "alphanumeric"
storageRequireEncryption = $true
scheduledActionsForRule = @(
@{
ruleName = "PasswordRequired"
scheduledActionConfigurations = @(
@{
actionType = "block"
gracePeriodHours = 24
notificationTemplateId = ""
notificationMessageCCList = @()
}
)
}
)
}
New-MgDeviceManagementDeviceCompliancePolicy -BodyParameter $compliancePolicy
# macOS Compliance Policy via Jamf Pro API
curl -X POST "https://jamf.company.com/api/v1/compliance-policies" \
-H "Authorization: Bearer ${JAMF_TOKEN}" \
-H "Content-Type: application/json" \
--data '{
"name": "Zero Trust - macOS Compliance",
"rules": [
{"type": "os_version", "operator": ">=", "value": "14.0"},
{"type": "filevault_enabled", "value": true},
{"type": "firewall_enabled", "value": true},
{"type": "gatekeeper_enabled", "value": true},
{"type": "sip_enabled", "value": true},
{"type": "auto_update_enabled", "value": true},
{"type": "screen_lock_timeout", "operator": "<=", "value": 300},
{"type": "falcon_sensor_running", "value": true}
]
}'Enable ZTA scoring and configure score thresholds for access tiers.
# CrowdStrike Falcon API: Query ZTA scores for all endpoints
curl -X GET "https://api.crowdstrike.com/zero-trust-assessment/entities/assessments/v1?ids=${DEVICE_AID}" \
-H "Authorization: Bearer ${CS_TOKEN}" \
-H "Content-Type: application/json"
# Response includes:
# {
# "aid": "device-agent-id",
# "assessment": {
# "overall": 82,
# "os": 90,
# "sensor_config": 85,
# "version": "7.14.16703"
# },
# "assessment_items": {
# "os_signals": [
# {"signal_id": "firmware_protection", "meets_criteria": "yes"},
# {"signal_id": "disk_encryption", "meets_criteria": "yes"},
# {"signal_id": "kernel_protection", "meets_criteria": "yes"}
# ],
# "sensor_signals": [
# {"signal_id": "sensor_version", "meets_criteria": "yes"},
# {"signal_id": "prevention_policies", "meets_criteria": "yes"}
# ]
# }
# }
# Define ZTA score thresholds for access tiers
# Tier 1 (Basic Access): ZTA >= 50
# Tier 2 (Standard Access): ZTA >= 65
# Tier 3 (Sensitive Access): ZTA >= 80
# Tier 4 (Critical Access): ZTA >= 90
# Query devices below minimum threshold
curl -X GET "https://api.crowdstrike.com/zero-trust-assessment/queries/assessments/v1?filter=assessment.overall:<50" \
-H "Authorization: Bearer ${CS_TOKEN}"
# CrowdStrike ZTA signals evaluated:
# - OS patch level and version
# - Disk encryption (BitLocker/FileVault)
# - Sensor version and configuration
# - Prevention policy enforcement
# - Firmware protection (Secure Boot)
# - Kernel protection (SIP, Code Integrity)
# - Firewall statusCreate conditional access policies that require compliant devices.
# Create Conditional Access policy requiring compliant device
Connect-MgGraph -Scopes "Policy.ReadWrite.ConditionalAccess"
$caPolicy = @{
displayName = "Zero Trust - Require Compliant Device"
state = "enabled"
conditions = @{
applications = @{
includeApplications = @("All")
}
users = @{
includeUsers = @("All")
excludeGroups = @("BreakGlass-Admins-Group-ID")
}
platforms = @{
includePlatforms = @("all")
}
clientAppTypes = @("browser", "mobileAppsAndDesktopClients")
}
grantControls = @{
operator = "AND"
builtInControls = @("mfa", "compliantDevice")
}
sessionControls = @{
signInFrequency = @{
value = 4
type = "hours"
isEnabled = $true
authenticationType = "primaryAndSecondaryAuthentication"
frequencyInterval = "timeBased"
}
persistentBrowser = @{
mode = "never"
isEnabled = $true
}
}
}
New-MgIdentityConditionalAccessPolicy -BodyParameter $caPolicy
# Create risk-based policy using device compliance + sign-in risk
$riskPolicy = @{
displayName = "Zero Trust - Block High Risk Sign-Ins on Non-Compliant Devices"
state = "enabled"
conditions = @{
applications = @{ includeApplications = @("All") }
users = @{ includeUsers = @("All") }
signInRiskLevels = @("high", "medium")
devices = @{
deviceFilter = @{
mode = "include"
rule = "device.isCompliant -ne True"
}
}
}
grantControls = @{
operator = "OR"
builtInControls = @("block")
}
}
New-MgIdentityConditionalAccessPolicy -BodyParameter $riskPolicySet up Okta device trust policies using CrowdStrike posture signals.
# Okta: Configure CrowdStrike device trust integration
# Admin Console > Security > Device Integrations > Add Integration
# Okta API: Create device assurance policy
curl -X POST "https://company.okta.com/api/v1/device-assurances" \
-H "Authorization: SSWS ${OKTA_API_TOKEN}" \
-H "Content-Type: application/json" \
--data '{
"name": "Corporate Device Assurance",
"platform": "WINDOWS",
"osVersion": {
"minimum": "10.0.19045"
},
"diskEncryptionType": {
"include": ["ALL_INTERNAL_VOLUMES"]
},
"screenLockType": {
"include": ["BIOMETRIC", "PASSCODE"]
},
"secureHardwarePresent": true,
"thirdPartySignalProviders": {
"dtc": {
"browserVersion": {
"minimum": "120.0"
},
"builtInDnsClientEnabled": true,
"chromeRemoteDesktopAppBlocked": true,
"crowdStrikeCustomerId": "CS_CUSTOMER_ID",
"crowdStrikeAgentId": "REQUIRED",
"crowdStrikeVerifiedState": {
"include": ["RUNNING"]
}
}
}
}'
# Create Okta authentication policy with device assurance
curl -X POST "https://company.okta.com/api/v1/policies" \
-H "Authorization: SSWS ${OKTA_API_TOKEN}" \
-H "Content-Type: application/json" \
--data '{
"name": "Zero Trust Application Policy",
"type": "ACCESS_POLICY",
"conditions": null,
"rules": [
{
"name": "Managed Device Access",
"conditions": {
"device": {
"assurance": {
"include": ["DEVICE_ASSURANCE_POLICY_ID"]
},
"managed": true,
"registered": true
},
"people": {
"groups": {"include": ["EMPLOYEES_GROUP_ID"]}
}
},
"actions": {
"appSignOn": {
"access": "ALLOW",
"verificationMethod": {
"factorMode": "1FA",
"type": "ASSURANCE"
}
}
}
},
{
"name": "Unmanaged Device - Block",
"conditions": {
"device": { "managed": false }
},
"actions": {
"appSignOn": { "access": "DENY" }
}
}
]
}'Set up real-time monitoring of device compliance state changes.
#!/usr/bin/env python3
"""Monitor device posture compliance drift in real-time."""
import requests
import time
import json
from datetime import datetime, timezone
CROWDSTRIKE_BASE = "https://api.crowdstrike.com"
INTUNE_BASE = "https://graph.microsoft.com/v1.0"
def get_cs_token(client_id: str, client_secret: str) -> str:
resp = requests.post(f"{CROWDSTRIKE_BASE}/oauth2/token", data={
"client_id": client_id,
"client_secret": client_secret
})
return resp.json()["access_token"]
def get_low_zta_devices(token: str, threshold: int = 50) -> list:
resp = requests.get(
f"{CROWDSTRIKE_BASE}/zero-trust-assessment/queries/assessments/v1",
headers={"Authorization": f"Bearer {token}"},
params={"filter": f"assessment.overall:<{threshold}", "limit": 100}
)
return resp.json().get("resources", [])
def get_intune_noncompliant(token: str) -> list:
resp = requests.get(
f"{INTUNE_BASE}/deviceManagement/managedDevices",
headers={"Authorization": f"Bearer {token}"},
params={
"$filter": "complianceState eq 'noncompliant'",
"$select": "id,deviceName,userPrincipalName,complianceState,lastSyncDateTime,operatingSystem"
}
)
return resp.json().get("value", [])
def check_posture_drift(cs_token: str, intune_token: str):
print(f"\n[{datetime.now(timezone.utc).isoformat()}] Device Posture Check")
print("=" * 60)
low_zta = get_low_zta_devices(cs_token, threshold=50)
print(f"CrowdStrike ZTA < 50: {len(low_zta)} devices")
noncompliant = get_intune_noncompliant(intune_token)
print(f"Intune Non-Compliant: {len(noncompliant)} devices")
for device in noncompliant[:10]:
print(f" - {device['deviceName']} ({device['userPrincipalName']}): "
f"{device['complianceState']} | Last sync: {device['lastSyncDateTime']}")
return {"low_zta_count": len(low_zta), "noncompliant_count": len(noncompliant)}| Term | Definition |
|---|---|
| Device Posture | Collection of endpoint security attributes (OS version, encryption, EDR status, patch level) evaluated before granting access |
| CrowdStrike ZTA Score | Numerical score (1-100) calculated by CrowdStrike Falcon assessing endpoint security posture based on OS signals and sensor configuration |
| Device Compliance Policy | MDM-defined rules specifying minimum security requirements (encryption, PIN, OS version) that devices must meet |
| Conditional Access | Policy engine (Entra ID, Okta) that evaluates user identity, device compliance, location, and risk before allowing access |
| Device Trust | Verification that an endpoint is managed, enrolled, and meets security baselines before treating it as trusted |
| Posture Drift | Degradation of device security posture over time (expired patches, disabled encryption) that should trigger access revocation |
Context: A healthcare company with 2,000 endpoints (70% Windows, 30% macOS) must enforce HIPAA-compliant device posture before allowing access to patient data systems. Devices are managed by Intune (Windows) and Jamf (macOS) with CrowdStrike Falcon deployed on all endpoints.
Approach:
Pitfalls: Grace periods must be long enough for IT to remediate but short enough to limit risk exposure. CrowdStrike ZTA scores can fluctuate with sensor updates; avoid setting thresholds too aggressively initially. BYOD devices may lack MDM enrollment; provide a separate Browser Access path with reduced functionality for unmanaged devices.
Device Posture Assessment Report
==================================================
Organization: HealthCorp
Report Date: 2026-02-23
Total Managed Devices: 2,000
COMPLIANCE BY PLATFORM:
Windows (1,400 devices):
Compliant: 1,302 (93.0%)
Non-compliant: 98 (7.0%)
Top Issue: Missing patches (45), BitLocker disabled (23)
macOS (600 devices):
Compliant: 567 (94.5%)
Non-compliant: 33 (5.5%)
Top Issue: OS outdated (18), FileVault disabled (8)
CROWDSTRIKE ZTA SCORES:
Average Score: 78.4
Devices >= 85 (Critical): 1,456 (72.8%)
Devices >= 70 (Standard): 1,812 (90.6%)
Devices < 50 (Blocked): 34 (1.7%)
CONDITIONAL ACCESS IMPACT (last 7 days):
Total sign-in attempts: 45,678
Blocked by posture: 312 (0.7%)
Remediated within 24h: 289 (92.6%)
Still non-compliant: 23
POSTURE DRIFT ALERTS:
Encryption disabled: 5
EDR sensor stopped: 3
OS downgraded: 1© 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
SKILL.md and 7 other files (scripts, references, assets) in skills/implementing-device-posture-assessment-in-zero-trust of mukul975/Anthropic-Cybersecurity-Skills.
Open the folder on GitHubat commit 54a7988
Implementing Device Posture Assessment In Zero Trust 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Implementing Device Posture Assessment In Zero Trust this skillmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~4.1k | Automated safety check: Pass | Apache-2.0 | |
| Frontmcp Authoritiesagentfront/frontmcp | 146 | — | ~7.1k | Automated safety check: Pass | Apache-2.0 | |
| Iam Auditbriiirussell/cybersecurity-skills | 413 | — | ~3.1k | Automated safety check: Notes | MIT | |
| Spring Security JWTrrezartprebreza/spring-boot-skills | 298 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Cometchat Securitycometchat/cometchat-skills | 131 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Glean Enterprise Rbacjeremylongshore/tons-of-skills-marketplace | 2.8k | — | ~1.5k | Automated safety check: Pass | MIT |
agentfront/frontmcp
A skill your agent uses when implementing authorization and access control for FrontMCP tools, resources, prompts, or skills, deciding who may invoke what.
briiirussell/cybersecurity-skills
Audit, design, and migrate Identity and Access Management — cloud provider IAM (AWS, GCP, Azure), identity providers (Okta, Entra ID / Azure AD, Auth0, Google Workspace), application authorization…
rrezartprebreza/spring-boot-skills
A skill your agent uses when an application issues and validates its own first-party JWT access and refresh tokens, including authentication filters, password encoding, RBAC, and method security.
cometchat/cometchat-skills
Enterprise auth & access control for CometChat — SSO/OIDC/SAML via your own IdP, server-minted auth tokens, token revocation & session control, and role-based access (RBAC app-wide roles + group…
jeremylongshore/tons-of-skills-marketplace
Map AD/Okta groups to Glean document permissions using allowedGroups.
ccashwell/evm-cortex
A skill your agent uses when performing initial audit reconnaissance.
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.
mukul975/Anthropic-Cybersecurity-Skills
Walks through reverse engineering Go-compiled malware in Ghidra: parsing buildinfo and pclntab, recovering stripped function names and extracting dependencies.
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.
mukul975/Anthropic-Cybersecurity-Skills
Hunts Windows malware persistence with Sysinternals Autoruns, covering run keys, services, scheduled tasks and drivers, with baseline comparison.
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.
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.
Works with
Categories
Implements device posture assessment as a zero trust access control by integrating endpoint health signals from CrowdStrike ZTA, Microsoft Intune, and Jamf into conditional access policies that…. Implementing Device Posture Assessment In Zero Trust is an agent skill from mukul975/Anthropic-Cybersecurity-Skills. Implements device posture assessment as a zero trust access control by integrating endpoint health signals from CrowdStrike ZTA, Microsoft Intune, and Jamf into conditional access policies that enforce compliance before granting access.
Implementing Device Posture Assessment In Zero Trust fits situations like: requiring device health checks before app access; wiring posture signals into conditional access; implementing the CISA Zero Trust device pillar.
Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-device-posture-assessment-in-zero-trust -a claude-code`. Or copy the skill folder (skills/implementing-device-posture-assessment-in-zero-trust in mukul975/Anthropic-Cybersecurity-Skills) into .claude/skills/implementing-device-posture-assessment-in-zero-trust in your project. Claude Code loads it when a task matches its description.
Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-device-posture-assessment-in-zero-trust -a codex`. Or copy the skill folder (skills/implementing-device-posture-assessment-in-zero-trust in mukul975/Anthropic-Cybersecurity-Skills) into .agents/skills/implementing-device-posture-assessment-in-zero-trust in your project. Codex loads it when a task matches its description.
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-device-posture-assessment-in-zero-trust -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-device-posture-assessment-in-zero-trust, .gemini/skills/implementing-device-posture-assessment-in-zero-trust, .github/skills/implementing-device-posture-assessment-in-zero-trust and .opencode/skills/implementing-device-posture-assessment-in-zero-trust in your project.
Going by SKILL.md and its folder, Implementing Device Posture Assessment In Zero Trust needs Python for the scripts in its folder, the command-line tools its instructions call (curl) and credentials named CS_TOKEN, OKTA_API_TOKEN and JAMF_TOKEN. Our summary lists: Python 3; A credential in JAMF_TOKEN; A credential in OKTA_API_TOKEN.
SKILL.md names 2 domains. In commands or code: api.crowdstrike.com and graph.microsoft.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
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.
Implementing Device Posture Assessment In Zero Trust 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.
About 4.1k tokens (SKILL.md is roughly 16k 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 1.8k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Implementing Device Posture Assessment In Zero Trust: Frontmcp Authorities (agentfront/frontmcp, 146 stars), Iam Audit (briiirussell/cybersecurity-skills, 413 stars), Spring Security JWT (rrezartprebreza/spring-boot-skills, 298 stars) and Cometchat Security (cometchat/cometchat-skills, 131 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
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.