Lead Enricher - Explorium AgentSource
ReviewAudited by ClawScan on May 1, 2026.
Overview
This appears to be a coherent Explorium lead-enrichment skill, but users should be aware it uses an API key, sends search/contact data to Explorium, and stores result files locally.
Before installing, make sure you are comfortable giving this skill access to your Explorium API key and allowing it to send lead-search inputs to Explorium. Keep the API key out of chat, review broad searches and enrichment requests before approving them, and clean up local result files if they contain sensitive prospect data.
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The agent may run the included CLI on the user's machine to call Explorium and read result files.
The skill is designed for the agent to run a local Python CLI. This is expected for the integration and is disclosed, but it is still local code execution users should recognize.
All API operations go through the `agentsource` CLI tool (`agentsource.py`).
Install and run the CLI only from a trusted copy of the skill, and review commands before allowing broad searches or exports.
The skill can act through the user's Explorium account and may consume account credits depending on the API operations performed.
The skill requires an Explorium API key and can use a locally stored credential to make authenticated API calls. This is purpose-aligned and clearly disclosed.
"name": "EXPLORIUM_API_KEY" ... "storage": "~/.agentsource/config.json (mode 600) or EXPLORIUM_API_KEY environment variable"
Use a scoped or revocable API key if available, do not paste the key into chat, and monitor Explorium usage/credits.
A broad query or enrichment request could retrieve many records, create CSV exports, and consume paid API credits.
The skill can perform high-volume fetch, enrichment, and export operations, but the documented flow includes preview and user confirmation before credit-consuming actions.
It shows you market statistics and a data sample before touching any credits ... You confirm — then it fetches your results and exports a downloadable CSV
Confirm entity type, filters, result limits, enrichment types, and export path before approving fetch/enrichment/export steps.
Lead/contact results and matching inputs may exist on disk temporarily and be transmitted to Explorium for processing.
The skill writes API results to local temp files and can send company/contact matching records and optional natural-language query text to Explorium. These flows are disclosed and aligned with the skill's purpose.
`/tmp/agentsource_*.json` | API result data | Cleaned up automatically by OS ... Company/contact records for matching ... `call_reasoning` ... Only when `--call-reasoning` is passed
Use the skill in a trusted environment, avoid opt-in call reasoning for private searches, and delete /tmp/agentsource_*.json files when results are no longer needed.