# Mail Security

> >-

- **Type:** Skill
- **Install:** `agentstack add skill-aashari-ai-agent-skills-mail-security`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [aashari](https://agentstack.voostack.com/s/aashari)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [aashari](https://github.com/aashari)
- **Source:** https://github.com/aashari/ai-agent-skills/tree/main/skills/apple-mail/mail-security

## Install

```sh
agentstack add skill-aashari-ai-agent-skills-mail-security
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Mail Security — Account Security Events

Scanning: **$ARGUMENTS** (default: last 30 days)

## Query
```bash
DB="$HOME/Library/Mail/V10/MailData/Envelope Index"
SINCE=$(($(date +%s) - 2592000))  # 30 days

sqlite3 "$DB" "
SELECT datetime(m.date_received,'unixepoch','localtime') as dt,
       s.subject, a.address as sender,
       mb.url as mailbox, m.ROWID, m.read
FROM messages m
JOIN subjects  s  ON m.subject = s.ROWID
JOIN addresses a  ON m.sender  = a.ROWID
JOIN mailboxes mb ON m.mailbox = mb.ROWID
WHERE m.date_received >= ${SINCE}
  AND m.deleted = 0
  AND mb.url NOT LIKE '%Spam%' AND mb.url NOT LIKE '%Trash%'
  AND (
    s.subject LIKE '%security alert%'
    OR s.subject LIKE '%sign-in%'
    OR s.subject LIKE '%sign in%'
    OR s.subject LIKE '%new sign%'
    OR s.subject LIKE '%login%'
    OR s.subject LIKE '%new device%'
    OR s.subject LIKE '%new login%'
    OR s.subject LIKE '%access from%'
    OR s.subject LIKE '%password%'
    OR s.subject LIKE '%two-factor%'
    OR s.subject LIKE '%two factor%'
    OR s.subject LIKE '%2FA%'
    OR s.subject LIKE '%2-step%'
    OR s.subject LIKE '%authenticator%'
    OR s.subject LIKE '%verification code%'
    OR s.subject LIKE '%suspicious%'
    OR s.subject LIKE '%unusual activity%'
    OR s.subject LIKE '%unauthorized%'
    OR s.subject LIKE '%account compromised%'
    OR s.subject LIKE '%verify your%'
    OR s.subject LIKE '%confirm your%'
    OR s.subject LIKE '%account locked%'
    OR s.subject LIKE '%reset your password%'
    OR s.subject LIKE '%forgot password%'
    OR s.subject LIKE '%recovery%'
    -- Senders
    OR a.address LIKE '%security@%'
    OR a.address LIKE '%accounts.google%'
    OR a.address LIKE '%account-security%'
    OR a.address LIKE '%noreply@%stripe%'
    OR a.address LIKE '%auth@%'
  )
ORDER BY m.date_received DESC;" 2>/dev/null
```

## Step 2: Parse for details
```bash
python3 ~/.claude/skills/_mail-shared/parser.py   ...
```

Extract from body:
- Service/platform name
- Event type (new login, 2FA enabled, password changed, etc.)
- Location/IP address of the event
- Device/browser info
- Timestamp of the security event (vs. email timestamp)
- Whether it offers a "this wasn't me" link

## Step 3: Flag suspicious events
Raise concern if:
- Login from unexpected location or country
- Multiple password reset emails in a short window
- 2FA changes you don't remember
- "New device" login you don't recognize
- Account recovery initiated you didn't start

## Output Format
**Security Events — [PERIOD]**

Group by type:
- 2FA Changes
- Password Resets
- New Device Logins
- Login from new location
- Suspicious Activity Alerts

For each event: Service | Event | Location/Device | Date | Status (read/unread)

Flag: any unread security alerts (you may not have seen them).
Flag: any events from unexpected locations.
Note: total count by account/service.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [aashari](https://github.com/aashari)
- **Source:** [aashari/ai-agent-skills](https://github.com/aashari/ai-agent-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-aashari-ai-agent-skills-mail-security
- Seller: https://agentstack.voostack.com/s/aashari
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.