OpenClaw Email Lead Generation

PassAudited by ClawScan on May 10, 2026.

Overview

No hidden or malicious behavior is evident, but the skill can store lead data, use email-account access, and run opt-in automated outreach jobs.

Before installing, decide whether you only want manual pipeline tracking or also want email integration and Tier 3 autopilot. Keep auto-send disabled unless you trust the configuration, review every email draft and exec approval, use dedicated email credentials where possible, and protect the ~/workspace/leadgen folder because it contains confidential lead 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.

What this means

The agent may create and modify files in the leadgen workspace through approved local commands.

Why it was flagged

The skill expects the agent to run local shell commands for setup and operation. This is disclosed and paired with user approval and helper-script guidance, but users should notice the local execution model.

Skill content
“You have the exec tool. USE IT. Run every command yourself via exec... Before each exec, briefly explain what the command does...”
Recommendation

Review each exec approval prompt and keep operations scoped to ~/workspace/leadgen as the skill instructs.

What this means

If configured, the skill could read relevant replies and send email through the user's email account.

Why it was flagged

The skill may use SMTP or Gmail credentials for email sending and inbox access. This is expected for an outreach tool, but it grants sensitive account authority.

Skill content
“optionalEnv”:[“SMTP_HOST”,“SMTP_PORT”,“SMTP_USER”,“SMTP_PASS”,“GMAIL_APP_PASSWORD”] ... “browser-based Gmail access (Tier 2 option)”
Recommendation

Use dedicated app passwords or scoped credentials where possible, and only enable email integration if you are comfortable with the access.

NoteHigh Confidence
ASI10: Rogue Agents
What this means

Enabled cron jobs can keep processing the pipeline after setup, including scheduled follow-ups under configured limits.

Why it was flagged

The skill can create persistent scheduled jobs that later trigger the agent and, if auto-send is enabled, send queued outreach automatically. The artifacts describe this as Tier 3 opt-in automation.

Skill content
“Tier 3 sets up 4 cron jobs via `openclaw cron add`. Each job triggers the agent...” and “If email method is `smtp` with auto-send: - Send automatically”
Recommendation

Only enable Tier 3/autopilot if you want ongoing automation, verify rate limits, and use the documented pause/disable flow when not needed.

What this means

Lead names, email addresses, company details, replies, and outreach history may remain on disk for future use.

Why it was flagged

The skill stores persistent lead, template, campaign, and reporting data that can be reused by later workflows and automated jobs.

Skill content
“Lead data stored as JSON files under ~/workspace/leadgen/. ... Templates and sequences are JSON. Config is YAML. Reports are markdown.”
Recommendation

Treat ~/workspace/leadgen as sensitive, avoid adding unnecessary private data, and review stored files before sharing or syncing the workspace.