Automatically logs into email accounts (Gmail, Outlook, QQ Mail, etc.) and generates daily email summaries. Use when the user wants to get a summary of their emails, check important messages, or create daily email digests.
Security checks across static analysis, malware telemetry, and agentic risk
Overview
The skill’s purpose is clear, but it uses logged-in email sessions, broad browser automation, and optional scheduling without enough credential and scope safeguards.
Install only if you are comfortable letting browser automation access your email account. Use a separate browser profile or limited mailbox, avoid entering passwords in shell commands, review any AI/provider use before sending mail content, and do not enable cron or launchd scheduling unless you want recurring unattended access.
Static analysis
Static analysis findings are pending for this release.
VirusTotal
64/64 vendors flagged this skill as clean.
Risk analysis
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.
The agent or browser automation could access all mail available in the logged-in session, and command-line password entry can expose credentials through shell history or process visibility.
The skill instructs use of an existing authenticated browser session and also shows entering an email password through a shell command, giving access to a full mailbox without a scoped credential boundary.
使用 `--browser real` 模式可以复用你 Chrome 浏览器中已登录的邮箱会话 ... browser-use input <password_input_index> "your-password"
Use a separate browser profile or a limited mailbox account, avoid typing real passwords into shell commands, and prefer provider-approved scoped/read-only access where possible.
A mistaken or overbroad command could read, capture, or interact with more of the email account than the user intended.
The skill allows any browser-use command and documents raw JavaScript/Python-style browser automation in authenticated webmail pages, which is broader than a narrowly scoped email-summary action.
allowed-tools: Bash(browser-use:*) ... browser-use eval "... document.querySelectorAll('tr.zA') ..." ... browser-use python "... html = browser.html ..."Require explicit user confirmation before opening authenticated mail, extracting data, taking screenshots, or running eval/python commands; limit actions to the specific mailbox and date range requested.
The actual browser automation code is supplied outside the reviewed skill artifact, so users depend on the external package and its current behavior.
The skill depends on an external CLI installation, but the registry declares no required binaries or install spec and the package version is not pinned.
uv pip install browser-use[cli] browser-use install
Install browser-use only from a trusted source, pin/review the package version, and understand what browser profile and data it can access.
Email subjects, senders, snippets, or message content could be processed by an external service if the AI extraction mode is used.
The optional AI extraction flow may send selected email metadata or content to a browser-use/AI provider, but the data boundary and retention are not described.
如果配置了 API Key，可以使用 AI 自动生成邮件摘要 ... browser-use extract "提取前 10 封邮件的发件人、主题和摘要，按重要性排序"
Do not use the AI extraction mode for sensitive mail unless you understand the provider, API key configuration, data retention, and privacy terms.
If configured, the summary job can keep opening the user’s email account every day without a fresh prompt.
The skill documents cron and launchd setup for recurring daily execution, creating ongoing mailbox access after initial setup.
0 9 * * * /path/to/email_daily_summary.sh >> /path/to/logs/email_summary.log 2>&1 ... launchctl load ~/Library/LaunchAgents/com.email.dailysummary.plist
Only enable scheduling intentionally, keep the script path and logs under your control, and add clear disable/unload instructions before using it.