Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Email Intelligence Agent

v1.0.6

Connect to IMAP mailboxes to classify emails by urgency, generate multi-language reply suggestions, and push summaries to Feishu in real time.

0· 118·0 current·0 all-time
byYK-Global@billjamno58

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for billjamno58/email-intelligence-agent.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Email Intelligence Agent" (billjamno58/email-intelligence-agent) from ClawHub.
Skill page: https://clawhub.ai/billjamno58/email-intelligence-agent
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install email-intelligence-agent

ClawHub CLI

Package manager switcher

npx clawhub@latest install email-intelligence-agent
Security Scan
Capability signals
CryptoCan make purchasesRequires sensitive credentials
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Pending
View report →
OpenClawOpenClaw
Suspicious
high confidence
!
Purpose & Capability
The code implements IMAP reading, AI classification, reply generation, and Feishu pushing which matches the description. However the registry metadata claims no required env vars/config paths while SKILL.md and the code require IMAP credentials (in config/config.yaml), AI provider credentials, Feishu push credentials, and SkillPay billing keys — this mismatch is incoherent and unexpected.
!
Instruction Scope
Runtime instructions and check_emails.py access environment variables (FEISHU_USER_ID, SKILL_BILLING_API_KEY, SKILL_BILLING_SKILL_ID) and a config file for IMAP credentials and AI config. The skill sends email summaries (including bodies) to Feishu and transmits FEISHU_USER_ID to an external billing endpoint (skillpay.me). SKILL.md asserts FEISHU_USER_ID is used only for billing and not stored/shared, but the code does transmit it to skillpay.me — the claim can't be independently verified and is a privacy risk.
Install Mechanism
No install spec — code is provided as files (Python scripts) and will be executed from source. That reduces installer-level risk, but the included code means the skill is not just an instruction-only manifest; users should inspect the scripts before running them.
!
Credentials
Requested credentials (IMAP username/password, Feishu webhook/app token, AI API key) are proportionate to function, but the registry advertises none. Additional required billing keys (SKILL_BILLING_API_KEY, SKILL_BILLING_SKILL_ID) and FEISHU_USER_ID are documented in SKILL.md and used in code. Transmitting FEISHU_USER_ID to skillpay.me is a non-obvious data flow and may be unexpected by users. The mismatch between declared requirements (none) and actual required secrets is a red flag.
Persistence & Privilege
The skill is not set always:true and does not modify other skills or system settings. However it can be invoked autonomously (default), and if granted credentials it can read email and push contents externally — autonomous invocation combined with the credential/data‑flow concerns increases risk and should influence deployment decisions.
What to consider before installing
Key things to consider before installing: 1) The registry metadata omits required secrets/config — SKILL.md and the scripts actually require IMAP credentials (in config/config.yaml), AI API keys, Feishu webhook/app token, and billing keys. That mismatch is suspicious; ask the publisher why the registry lists no required env vars or config paths. 2) The skill transmits FEISHU_USER_ID to an external billing endpoint (https://skillpay.me). If you care about privacy, verify that you trust that service and the payment flow. 3) The code will read full email bodies and can push them to Feishu — limit the account access you give (use app-specific passwords, read-only IMAP, and a minimal Feishu webhook with a dedicated bot or channel). 4) Because the package includes runnable Python scripts, inspect or run them in a sandbox before providing real credentials. 5) If you allow autonomous invocation, consider the blast radius: an autonomous run with valid IMAP credentials could transmit email contents to external services. 6) Prefer installing only from a known/published source (homepage, repo, or verified publisher). If you proceed, test with a throwaway mailbox and minimal permissions first.

Like a lobster shell, security has layers — review code before you run it.

latestvk9747f1mkwks0hf3xj5tpcvsv985htba
118downloads
0stars
7versions
Updated 3d ago
v1.0.6
MIT-0

Email Intelligence Agent

IMAP Email Read → AI Classification → Reply Suggestions → Feishu Push Summary

Slug: email-intelligence-agent Price: $0.01 USDT per call Author: 91Skillhub Team


Overview

FeatureDescription
IMAP Email ReadConnect to any IMAP mailbox (QQ/163/Enterprise/Gmail, etc.)
AI ClassificationUrgent / Important / Normal / Can Wait
Reply SuggestionsAI generates multilingual reply suggestions, confirmed by user before sending
Feishu PushSummary card pushed to Feishu group or DM

Tiered Features

FeatureFREEPRO
Email read & classificationKeyword-basedAI-powered
Reply suggestionsYes
Feishu pushYes
Max emails per run10Unlimited
PriceFree$0.01/call

Quick Start

1. Configure Email (IMAP)

IMAP Config:
- Server: imap.example.com
- Port: 993 (SSL)
- Username: your@email.com
- Password: App-specific password (NOT your login password)

Tip: Use an App Password from your email provider's security settings

2. Configure AI API

Supports OpenAI-compatible API (OpenAI, Claude, domestic models, etc.)

3. Configure Feishu Push

Set up a Feishu bot webhook or user_id to receive push notifications.


Classification Labels

LabelExample Keywords
Urgentrefund, cancel order, complaint, negative review, urgent
Importantafter-sales, repair, payment, invoice, account issue
Normalinquiry, price, specs, logistics, shipping
Can Waithello, thank you, goodbye, already handled

Billing

  • Pay-per-call: $0.0100 USDT per execution via SkillPay.me
  • Balance insufficient: Payment URL returned — top up at https://skillpay.me/email-intelligence-agent
  • External data flow: FEISHU_USER_ID transmitted to skillpay.me/api/v1/billing for billing identification only; not stored or shared with any third party
  • Billing model: Each run = 1 call = $0.0100 USDT
  • Privacy: FEISHU_USER_ID is used solely to identify the billing account; no personal data is retained or shared beyond the payment processor

Required Environment Variables

VariableDescription
SKILL_BILLING_API_KEYSkillPay Builder API Key
SKILL_BILLING_SKILL_IDSkillPay Skill ID (email-intelligence-agent)
FEISHU_USER_IDUser open_id for billing (passed by Feishu runtime)

Directory Structure

email-customer-assistant/
├── SKILL.md
├── scripts/
│   ├── check_emails.py      # Main script + billing
│   ├── imap_client.py       # IMAP connection wrapper
│   ├── classifier.py         # Keyword + AI classifier
│   ├── reply_generator.py    # Reply generator
│   └── feishu_pusher.py      # Feishu pusher
└── requirements.txt

Usage Limits

  • Read-only emails — no sending or deleting
  • IMAP access only — no direct platform API calls
  • Complies with email provider terms of service

License

MIT

Comments

Loading comments...