EdgeIQ Lead Researcher

Enrich company data from a name, LinkedIn URL, or domain with size, industry, tech stack, news, social links, and contact info via passive HTTP analysis.

Security Scan

The skill's code and instructions align with its stated purpose (passive HTTP enrichment of companies) — the only notable inconsistency is that the docs and code reference an optional TAVILY_API_KEY but the registry metadata does not declare any required environment variables.

Purpose & Capability

Name/description promise passive HTTP-based enrichment (size, industry, tech stack, news, social, contacts). The included Python code and README implement HTTP requests, header/meta/script inspection, path checks, simple heuristics and optional news lookups — all coherent with the described capability. There are no unrelated binaries or surprising system-level requirements.

Instruction Scope

SKILL.md instructs only to perform passive HTTP/HTTPS requests, inspect headers and HTML, and optionally call a news API (Tavily) or DuckDuckGo fallback. It warns to respect robots.txt. The runtime behavior described (and the visible code) stays within that scope; it does not instruct reading arbitrary local files beyond optional CSV output or environment variables for an API key.

Install Mechanism

There is no install spec and the code uses Python stdlib only. No external package downloads or archive extraction are requested, which is low risk.

Credentials

SKILL.md/README and the code reference an optional TAVILY_API_KEY (and the CLI supports --tavily-key and mentions .env), but the registry metadata lists no required environment variables. This is an inconsistency: the skill will read an env var if present but the registry does not declare it. Otherwise, no unrelated secrets or broad credentials are requested.

Persistence & Privilege

The skill does not request always:true and does not modify other skills or system-wide settings. It runs on demand and does not ask for persistent elevated privileges.

Assessment

This skill appears to do what it says: passive HTTP lookups and heuristic enrichment. Before installing or running: 1) Be aware it makes outbound HTTP(S) requests to any domain you provide and may call third-party APIs (Tavily or search fallbacks) — do not pass sensitive internal hostnames. 2) The docs and code reference TAVILY_API_KEY (and a .env example) but the registry metadata does not declare any env vars — only provide an API key if you trust the skill and the Tavily service. 3) The User-Agent string contains a link to edgeiq.dev (harmless but identifiable); check the code if you prefer a different UA. 4) Because it writes CSV output if you request it, validate output paths to avoid accidental overwrite. 5) If you need higher assurance, run the skill in an isolated environment (container) and/or inspect the full Python file to confirm there are no unexpected outbound endpoints or obfuscated logic. Finally, consider asking the publisher for a homepage or source repository to improve trust — the registry entry currently lacks a public homepage.

SKILL.md — Lead Researcher by EdgeIQ Labs

Version: 1.0.0
Category: Business Intelligence / Lead Generation
Author: EdgeIQ Labs
Python: 3.12+

---

What It Does

Lead Researcher takes a company name, LinkedIn URL, or domain as input and returns enriched lead data including company size, industry, tech stack (Wappalyzer-style HTTP header/fingerprint detection), recent news, social links, and contact enrichment.

Output is structured JSON or human-readable formatted text. Pro tier adds CSV export.

---

Pricing Tiers

Feature	Free	Pro ($19/mo)	Bundle ($39/mo)
Lookups/month	3	50	Unlimited
Basic enrichment	✅	✅	✅
Tech stack detection	✅	✅	✅
News/press articles	—	✅	✅
Social links	—	✅	✅
Contact enrichment	—	Basic	Full
CSV export	—	✅	✅
Priority support	—	—	✅

---

Usage

python3 /path/to/lead_researcher.py "Acme Corp"
python3 /path/to/lead_researcher.py "https://www.linkedin.com/company/acme-corp"
python3 /path/to/lead_researcher.py "acme.com"
python3 /path/to/lead_researcher.py "acme.com" --format json
python3 /path/to/lead_researcher.py "acme.com" --format csv --output acme_leads.csv
python3 /path/to/lead_researcher.py "acme.com" --tier pro

Arguments

• input — Company name, LinkedIn URL, or domain
• --format — Output format: text (default) or json
• --output — File path for CSV export (Pro tier)
• --tier — Tier override: free, pro, or bundle (default: free behavior)
• --tavily-key — Override Tavily API key (defaults to env TAVILY_API_KEY)

---

Legal Notice

⚠️ Only research companies you have legitimate business interest in. Do not use for spam or unsolicited contact. This tool aggregates publicly available information. Respect robots.txt and terms of service of scraped sources.

---

Tech Stack Detection

The skill performs passive HTTP-based tech fingerprinting:

1. Makes HTTP/HTTPS requests to the target domain
2. Inspects HTTP headers (Server, X-Powered-By, CF-* headers, etc.)
3. Checks for common JavaScript framework meta tags in HTML
4. Looks at default paths (favicon, /wp-login.php, /.well-known/, etc.)
5. Compares headers and patterns against a built-in signature database

No active scanning. No port probes. Passive reconnaissance only.

---

Output Schema

{
  "company": "Acme Corp",
  "domain": "acme.com",
  "size": "50-200",
  "industry": "Software",
  "description": "...",
  "tech_stack": ["WordPress", "Cloudflare", "Google Analytics", "Stripe"],
  "news": [{"title": "...", "url": "...", "date": "..."}],
  "social": {"linkedin": "...", "twitter": "...", "facebook": "..."},
  "contacts": [{"name": "...", "title": "...", "linkedin": "..."}],
  "lookup_date": "2026-04-23"
}