SentinelOne Threat Intel and CVE Lookup
Overview
Alongside the Singularity data tools, the SentinelOne connector (Purple MCP sidecar) serves enrichment tools backed by VirusTotal / Google Threat Intelligence and a CVE database. They answer "what is this indicator?" and "what is this CVE?" without leaving the investigation. None of them touches a customer endpoint or the SentinelOne console.
Anti-triggers
- Alert triage itself — use
sentinelone-alerts.
- Vulnerabilities found on the customer's endpoints — that is SentinelOne's own vulnerability data; use
sentinelone-vulnerabilities. The CVE tools here describe a CVE in general, not which hosts have it.
- Hunting in the customer's telemetry — use
sentinelone-threat-hunting (powerquery, purple_ai).
MCP Tools
| Tool |
Arguments |
Returns |
threat_intel_by_hash |
hash_value (MD5, SHA-1 or SHA-256) |
Detection ratio, names, first/last seen, classification |
threat_intel_by_ip |
ip_address |
Reputation, ASN/owner, related detections |
threat_intel_by_domain |
domain |
Reputation, registration, related detections |
threat_intel_by_url |
url |
Reputation and scan verdicts |
threat_intel_get_file_behavior |
hash_value, optional sandbox |
Sandbox execution report: processes, file and registry activity, network traffic |
threat_intel_get_file_relationships |
hash_value, relationship_type |
Network IOCs and related files from the file's analysis |
threat_intel_search |
query (VirusTotal Intelligence syntax) |
Files matching an advanced query |
cve_search_by_id |
cve_id, e.g. CVE-2024-3400 |
Description, CVSS score, references for one CVE |
cve_search_by_vendor |
vendor, optional product |
CVEs affecting a vendor/product |
cve_database_status |
— |
When the CVE database was last updated and how many CVEs it holds |
Tier: none of these tools is classified in Conduit yet, so all of them enforce at admin. See GOVERNANCE.md.
{ "tool": "threat_intel_by_hash", "arguments": { "hash_value": "44d88612fea8a8f36de82e1278abb02f" } }
{ "tool": "threat_intel_by_domain", "arguments": { "domain": "login-contoso-support.example" } }
{ "tool": "threat_intel_by_url", "arguments": { "url": "https://login-contoso-support.example/reset" } }
The VirusTotal tools need a VirusTotal API key on the server (PURPLEMCP_VT_API_KEY in Purple MCP). If they fail with an authentication error, the key is missing; the CVE tools do not need it.
Workflows
Enrich an alert's indicators
get_alert (and get_alert_investigation_report for Purple AI's auto-investigation, if one ran) to collect the file hash, IPs, domains and URLs.
threat_intel_by_hash for the file; if detections are low but the alert is suspicious, threat_intel_get_file_behavior for what it does when run.
threat_intel_by_ip / threat_intel_by_domain / threat_intel_by_url for each network indicator.
threat_intel_get_file_relationships to pivot from the file to its contacted infrastructure, then check whether those indicators appear elsewhere in the fleet with powerquery.
- Summarise as known-bad, known-good, or unknown, with the evidence for each indicator.
CVE question from a customer
cve_database_status so the answer can state how current the data is.
cve_search_by_id for a named CVE, or cve_search_by_vendor (with product) for "what affects our Fortinet firewalls?".
- To find which customer endpoints are actually exposed, switch to
sentinelone-vulnerabilities.
Gotchas
- Third-party lookups leave the tenant. Hashes, IPs, domains and URLs are sent to VirusTotal / Google Threat Intelligence. Do not submit indicators the customer considers confidential (internal hostnames, URLs with tokens).
- A clean result is not proof of safety. A hash VirusTotal has never seen returns little or nothing; treat that as "unknown", not "benign".
- Rate limits. Threat-intel lookups are quota-bound upstream. Enrich the indicators that matter rather than every row of a hunt result. On a quota or rate-limit error, do not retry in a loop: wait a minute and retry once, then defer the rest and report those indicators as unverified.
Related Skills
1---2name: sentinelone-threat-intel-and-cve-lookup3description: >4 The SentinelOne sidecar's enrichment tools: VirusTotal / Google Threat5 Intelligence lookups by hash, IP, domain and URL (threat_intel_*), sandbox6 behaviour and file relationships, advanced VirusTotal search, and the CVE7 database (cve_search_by_id, cve_search_by_vendor, cve_database_status).8when_to_use: >-9 When enriching an indicator from a SentinelOne alert or hunt, or looking up a CVE. Use when:10 is this hash malicious, virustotal lookup, check this ip, domain reputation, url reputation,11 file sandbox behaviour, cve lookup, cves for a vendor, or ioc enrichment.12metadata:13 source: https://skillmd.com/skills/wyre-ai/sentinelone-threat-intel-and-cve-lookup14---1516# SentinelOne Threat Intel and CVE Lookup1718## Overview1920Alongside the Singularity data tools, the SentinelOne connector (Purple MCP sidecar) serves enrichment tools backed by VirusTotal / Google Threat Intelligence and a CVE database. They answer "what is this indicator?" and "what is this CVE?" without leaving the investigation. None of them touches a customer endpoint or the SentinelOne console.2122## Anti-triggers2324- **Alert triage itself** — use `sentinelone-alerts`.25- **Vulnerabilities found on the customer's endpoints** — that is SentinelOne's own vulnerability data; use `sentinelone-vulnerabilities`. The CVE tools here describe a CVE in general, not which hosts have it.26- **Hunting in the customer's telemetry** — use `sentinelone-threat-hunting` (`powerquery`, `purple_ai`).2728## MCP Tools2930| Tool | Arguments | Returns |31|------|-----------|---------|32| `threat_intel_by_hash` | `hash_value` (MD5, SHA-1 or SHA-256) | Detection ratio, names, first/last seen, classification |33| `threat_intel_by_ip` | `ip_address` | Reputation, ASN/owner, related detections |34| `threat_intel_by_domain` | `domain` | Reputation, registration, related detections |35| `threat_intel_by_url` | `url` | Reputation and scan verdicts |36| `threat_intel_get_file_behavior` | `hash_value`, optional `sandbox` | Sandbox execution report: processes, file and registry activity, network traffic |37| `threat_intel_get_file_relationships` | `hash_value`, `relationship_type` | Network IOCs and related files from the file's analysis |38| `threat_intel_search` | `query` (VirusTotal Intelligence syntax) | Files matching an advanced query |39| `cve_search_by_id` | `cve_id`, e.g. CVE-2024-3400 | Description, CVSS score, references for one CVE |40| `cve_search_by_vendor` | `vendor`, optional `product` | CVEs affecting a vendor/product |41| `cve_database_status` | — | When the CVE database was last updated and how many CVEs it holds |4243**Tier:** none of these tools is classified in Conduit yet, so all of them enforce at `admin`. See `GOVERNANCE.md`.4445```json46{ "tool": "threat_intel_by_hash", "arguments": { "hash_value": "44d88612fea8a8f36de82e1278abb02f" } }47{ "tool": "threat_intel_by_domain", "arguments": { "domain": "login-contoso-support.example" } }48{ "tool": "threat_intel_by_url", "arguments": { "url": "https://login-contoso-support.example/reset" } }49```5051The VirusTotal tools need a VirusTotal API key on the server (`PURPLEMCP_VT_API_KEY` in Purple MCP). If they fail with an authentication error, the key is missing; the CVE tools do not need it.5253## Workflows5455### Enrich an alert's indicators56571. `get_alert` (and `get_alert_investigation_report` for Purple AI's auto-investigation, if one ran) to collect the file hash, IPs, domains and URLs.582. `threat_intel_by_hash` for the file; if detections are low but the alert is suspicious, `threat_intel_get_file_behavior` for what it does when run.593. `threat_intel_by_ip` / `threat_intel_by_domain` / `threat_intel_by_url` for each network indicator.604. `threat_intel_get_file_relationships` to pivot from the file to its contacted infrastructure, then check whether those indicators appear elsewhere in the fleet with `powerquery`.615. Summarise as known-bad, known-good, or unknown, with the evidence for each indicator.6263### CVE question from a customer64651. `cve_database_status` so the answer can state how current the data is.662. `cve_search_by_id` for a named CVE, or `cve_search_by_vendor` (with `product`) for "what affects our Fortinet firewalls?".673. To find which customer endpoints are actually exposed, switch to `sentinelone-vulnerabilities`.6869## Gotchas7071- **Third-party lookups leave the tenant.** Hashes, IPs, domains and URLs are sent to VirusTotal / Google Threat Intelligence. Do not submit indicators the customer considers confidential (internal hostnames, URLs with tokens).72- **A clean result is not proof of safety.** A hash VirusTotal has never seen returns little or nothing; treat that as "unknown", not "benign".73- **Rate limits.** Threat-intel lookups are quota-bound upstream. Enrich the indicators that matter rather than every row of a hunt result. On a quota or rate-limit error, do not retry in a loop: wait a minute and retry once, then defer the rest and report those indicators as unverified.7475## Related Skills7677- [Alerts](../alerts/SKILL.md)78- [Threat Hunting](../threat-hunting/SKILL.md)79- [Vulnerabilities](../vulnerabilities/SKILL.md)