email-agent
Process CRM Emails with AI Insights
Teams lose time turning inbound emails into CRM updates. This skill triages unprocessed emails, links contacts, extracts intent, and records audit logs.
Stop for confirmation before installing.
Review the plan and obtain explicit user consent before changing files.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "email-agent" from https://skillstore.io/skills/cleanexpo-email-agent.md and its manifest at https://skillstore.io/api/skills/cleanexpo-email-agent/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "email-agent". Process emails for Duncan workspace.
Expected outcome:
Email processing complete. The agent processed 12 messages, linked 9 contacts, created 3 contacts, and flagged 4 warm leads.
Using "email-agent". Analyze unprocessed emails and show follow-up needs.
Expected outcome:
The inbox contains pricing requests, partnership inquiries, and one support complaint. Three contacts should receive priority follow-up today.
Using "email-agent". Process one warm lead email.
Expected outcome:
The sender was linked to an existing contact. The message was positive, had inquiry intent, and added a new CRM note.
Security Audit
High RiskAll static external-command findings are false positives caused by Markdown code fences and inline code formatting. Semantic review found hardcoded tenant identifiers and automated CRM mutation instructions that could alter email and contact records when live Convex access is available. No prompt injection attempt was found.
Confirmed security concerns (2)
Risk Factors
⚙️ External commands (21)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/cleanexpo-email-agent/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/cleanexpo-email-agent?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/cleanexpo-email-agent?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/cleanexpo-email-agent/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/cleanexpo-email-agent.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
CleanExpo. (2026). email-agent security audit report (audit version 8) [Author version unspecified]. Skillstore. https://skillstore.io/skills/cleanexpo-email-agent/audits/8BibTeX citation
@techreport{cleanexpo-cleanexpo-email-agent-2026,
author = {CleanExpo},
title = {email-agent security audit report (audit version 8)},
institution = {Skillstore},
year = {2026},
number = {8},
url = {https://skillstore.io/skills/cleanexpo-email-agent/audits/8},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "email-agent security audit report (audit version 8)"
version: "unspecified"
type: report
authors:
- name: "CleanExpo"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/cleanexpo-email-agent/audits/8"
identifiers:
- type: other
value: "skillstore:cleanexpo-email-agent:audit:8"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Triage inbound sales emails
Convert new email activity into contact records, intent labels, sentiment labels, and follow-up cues.
Maintain CRM interaction history
Attach summarized email interactions to contact notes and keep audit records for later review.
Prioritize warm leads
Identify contacts with positive sentiment and inquiry intent so teams can focus outreach.
Try These Prompts
Process unprocessed emails for the configured workspace and summarize the results.
Analyze unprocessed emails, list detected intents and sentiment, and flag messages that need manual follow-up before updates.
Process new workspace emails, link each sender to a contact, update CRM notes, and include a concise audit summary.
Process up to 20 unprocessed emails, skip ambiguous senders, report contact changes, and identify records needing human review.
Best Practices
- Run a dry review before allowing record updates in shared workspaces.
- Confirm the target org and workspace before processing email batches.
- Review high-priority leads after each processing summary.
Avoid
- Do not run the workflow with hardcoded tenant IDs in a public marketplace setting.
- Do not process private email bodies without an approved data handling policy.
- Do not rely only on keyword rules for high-value or sensitive customer decisions.