Ironclaw Lead Enrichment
PassAudited by ClawScan on May 10, 2026.
Overview
The skill is coherent for lead enrichment, but it can search public sources, infer emails, persist checkpoints, and bulk-update CRM records, so users should scope and review runs.
Before installing, confirm the exact CRM table or lead list to enrich, review the external LinkedIn scraper/tool permissions, keep backups or a change log, and require approval before writing inferred emails or low-confidence matches.
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.
Incorrect or low-confidence enriched data could be written across a CRM dataset.
The skill instructs bulk CRM data reads and writes through DuckDB. This is central to lead enrichment, but it can change many business records.
For enriching many records at once: ... Query all incomplete records from DuckDB ... UPDATE v_leads SET
Run on a clearly selected lead list, keep a backup or change log, and require review before writing low-confidence or inferred fields.
Actual LinkedIn scraping behavior and data handling depend on an unreviewed external skill.
The skill relies on a separate linkedin-scraper skill, but the provided artifacts do not identify its source, version, permissions, or behavior.
LinkedIn (via linkedin-scraper skill) — name, title, company, education, connections
Use only a trusted, reviewed linkedin-scraper skill and confirm its permissions and terms before enrichment.
Personal lead data or enrichment progress may be stored outside the primary CRM record in an unspecified checkpoint.
The workflow processes personal lead fields such as email, LinkedIn URL, title, company, location, and education, then instructs saving checkpoints without specifying storage location or retention.
Save checkpoint after each batch (in case of interruption)
Define where checkpoints are stored, what fields they include, who can access them, and when they are deleted.
A wrong company match or email pattern could create many incorrect CRM updates.
The skill may apply inferred company-level data or guessed email patterns across multiple records, so one bad assumption can affect a batch.
Group by company (scrape company once, apply to all employees) ... Use the most common pattern as fallback
Require confidence labels, sample-check batches, and avoid automatically writing fallback guesses without user approval.