{% extends "base.html" %} {% block title %}Data sources — {{ site_name }}{% endblock %} {% block content %}
Every source is queried in parallel and weighted by how strongly it asserts a verdict. Sources marked context add enrichment only — they never change the verdict.
| Source | Supports | Category | Auth | Status |
|---|---|---|---|---|
|
{% if s.homepage %}{{ s.display }}
{% else %}{{ s.display }}{% endif %}
{{ s.name }}
|
{{ s.kinds|join(', ') }} | {{ s.category }} | {{ 'none' if s.keyless else (s.env_key or 'none') }} |
{# green is reserved for verdicts and for real health; "enabled" is
not a finding, so an active source is a plain neutral tag. #}
{% if s.state == 'active' %}active
{% elif s.state == 'disabled' %}off
{% else %}needs key{% endif %}
{% if s.state == 'disabled' and s.opt_in %}
set {{ s.opt_in }}=1
{% endif %}
{% if s.quota %}
{% if s.quota.limit is not none %}{{ s.quota.used }}/{{ s.quota.limit }} today
{% else %}{{ s.quota.used }} today{% endif %}
{% if s.quota.shared > 1 %} · shared by {{ s.quota.shared }} sources{% endif %}
{% if s.quota.exhausted %} · spent{% endif %}
{% endif %}
|
Set the environment variable and restart the service. Keys are never sent to the browser or logged.
# /etc/threattrove/threattrove.env ABUSECH_AUTH_KEY=... # auth.abuse.ch — MalwareBazaar, ThreatFox, URLhaus VT_API_KEY=... # virustotal.com — files, URLs, domains, IPs MD_API_KEY=... # metadefender.com — files, URLs, domains, IPs OTX_API_KEY=... # otx.alienvault.com (optional, raises limits) URLSCAN_API_KEY=... # urlscan.io (optional, raises limits) HA_API_KEY=... # hybrid-analysis.com MALSHARE_API_KEY=... # malshare.com TRIAGE_API_KEY=... # tria.ge GSB_API_KEY=... # Google Safe Browsing v4 (non-commercial use) PHISHTANK_APPKEY=... # phishtank.com
The free sources (CIRCL hashlookup, AlienVault OTX, urlscan.io search,
DNS, RDAP and Certificate Transparency) answer without any key, so a fresh
install is useful immediately. Reverse IP lookups are free but rate
limited, so they stay off until you set TT_ENABLE_REVERSE_IP=1.
The three VirusTotal sources spend one key's allowance between them: a
lookup of a hash, a URL and a domain is three requests. The app keeps a
per-day counter and stops asking once the budget is gone, so a busy day
ends with “budget spent” answers instead of rate-limit errors. Raise or
lower it with TT_VT_DAILY_BUDGET (default 400; the free key
allows 500).
VirusTotal's domain and IP lookup is off by default
(TT_VT_DOMAINS=1 turns it on). A stray engine flag on a shared
IP address or a popular domain says almost nothing, so this endpoint mostly
buys noise, and the allowance is better spent on files and URLs.
Google Safe Browsing and PhishTank are blocklists, not clearances. A URL that neither lists is reported as “no match” with no verdict, the same as a source with no key: not being on a list is not a statement that a URL is safe. Safe Browsing's API is licensed for non-commercial use only.
PhishTank currently sits behind a Cloudflare challenge that refuses non-browser clients, so in practice it answers “upstream blocks API clients (Cloudflare)” and makes no claim either way. When it does answer, only a record that is both valid and verified counts as phishing.
The MetaDefender sources spend their own key and their own allowance: one
counter for the file, URL and domain/IP endpoints together, default 800 a
day (TT_MD_DAILY_BUDGET, the community key allows 1000) and one
call every 7.2 seconds (TT_MD_MIN_INTERVAL, the key allows 500
an hour).
Two engine panels are still one kind of evidence. VirusTotal and MetaDefender agree or they do not, but neither can convict a file on its own: both count as the same engine panel authority, and a malicious verdict still needs a second, independent authority — a sample feed, a sandbox, or your own blocklist.