Install
$ agentstack add skill-adrojis-tracecat-skills-tracecat-integration-expert ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Tracecat Integration Expert
You are an expert at configuring and using Tracecat integrations with external security tools and services.
Integration Naming Convention
All integrations follow: tools..
Common Integrations
Threat Intelligence
| Integration | Actions | Secret Required | |------------|---------|-----------------| | VirusTotal | analyze_url, analyze_hash, get_report | virustotal (apikey) | | AbuseIPDB | check_ip, report_ip | abuseipdb (apikey) | | GreyNoise | check_ip, query | greynoise (apikey) | | Shodan | search, host_info | shodan (apikey) | | AlienVault OTX | get_indicators | otx (api_key) |
EDR / Endpoint
| Integration | Actions | Secret Required | |------------|---------|-----------------| | CrowdStrike | contain_host, lift_containment, search_detections | crowdstrike (clientid, clientsecret) | | SentinelOne | isolate_agent, get_threats | sentinelone (apikey, url) | | Microsoft Defender | isolate_machine, get_alerts | msdefender (tenantid, clientid, clientsecret) |
SIEM
| Integration | Actions | Secret Required | |------------|---------|-----------------| | Splunk | search, create_alert | splunk (token, url) | | Elastic | search, get_alerts | elastic (api_key, url) |
Communication
| Integration | Actions | Secret Required | |------------|---------|-----------------| | Slack | post_message, create_channel | slack (bottoken) | | PagerDuty | create_incident, acknowledge | pagerduty (apikey) | | Email (SMTP) | send_email | smtp (host, port, user, password) |
Identity
| Integration | Actions | Secret Required | |------------|---------|-----------------| | Okta | suspend_user, reset_password | okta (apikey, domain) | | Azure AD | disable_user, revoke_sessions | azuread (tenantid, clientid, clientsecret) |
Setting Up an Integration
1. Create the secret
Use tracecat_create_secret with:
name: "virustotal"
type: "custom"
keys: [{ key: "api_key", value: "YOUR_API_KEY" }]
2. Use in workflow YAML
- ref: check_hash
action: tools.virustotal.analyze_hash
args:
hash: ${{ TRIGGER.data.file_hash }}
The secret is automatically resolved by Tracecat based on the integration name.
Custom Integrations
For services without built-in integration, use core.http.request:
- ref: custom_api_call
action: core.http.request
args:
method: POST
url: https://api.example.com/v1/endpoint
headers:
Authorization: "Bearer ${{ SECRETS.custom_api.token }}"
Content-Type: application/json
payload:
data: ${{ TRIGGER.data }}
Best Practices
- Secret naming — Use the integration name as the secret name
- Least privilege — Use API keys with minimum required permissions
- Rate limiting — Add delays between bulk API calls
- Error handling — Always handle API errors gracefully in workflows
- Testing — Test integrations with non-destructive actions first
Related Skills
- tracecat-secrets-integrations — Detailed secret configuration and integration setup (replaces this skill for secrets)
- tracecat-action-configuration — Action types and input configuration
- tracecat-mcp-tools-expert — MCP tool reference for secrets and actions
- tracecat-workflow-patterns — Workflow design patterns using integrations
- tracecat-yaml-syntax — YAML syntax for integration inputs
- tracecat-validation-debug — Debug integration errors (HTTP 4xx/5xx)
- tracecat-code-python — Custom integrations via Python scripts
Reference Files
- [Common Mistakes](./COMMON_MISTAKES.md)
- [Examples](./EXAMPLES.md)
- [README](./README.md)
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: adrojis
- Source: adrojis/tracecat-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.