QQemail-agent
v1.0.0QQ邮箱接收与发送skill - 读取QQ邮箱中的邮件和发送邮件到其他账号
⭐ 0· 244·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (QQ 邮箱收发) align with included scripts (fetch_orders.py reads IMAP, send_email.py sends via SMTP) and declared dependencies (imap-tools, python-dotenv). No unrelated env vars, binaries, or config paths are requested.
Instruction Scope
SKILL.md instructs the agent to collect the user's QQ email and authorization code and write them into a local .env file; the scripts read that .env and perform only mailbox access and email sending. This is within scope, but collecting secrets via chat and persisting them in plaintext is a privacy/security concern (expected for purpose, but worth highlighting).
Install Mechanism
No install spec — instruction-only plus small Python scripts. Dependencies are standard Python packages from PyPI (imap-tools, python-dotenv). No downloads from arbitrary URLs or archive extraction are present.
Credentials
The skill needs IMAP/SMTP credentials (authorization code) which are proportionate to its purpose. The package does not request other unrelated secrets. However, it encourages the user to paste the authorization code into the chat and to persist it in a plain .env file, which increases risk of credential exposure if the agent/chat logs or disk are not secured.
Persistence & Privilege
always is false and the skill is user-invocable; it does not attempt to modify other skills or system-wide settings. Its persistent effect is limited to creating/reading a local .env in the working directory (normal for this kind of tool).
Assessment
This skill appears to do what it claims (read/send QQ mail). Before installing/using: (1) Prefer generating an app-specific authorization code (not your QQ login password); (2) Do not paste secrets into public/shared chat history — if you must provide the auth code to an agent, ensure the agent runs locally or that the platform protects chat contents; (3) Restrict permissions of the .env file (e.g., chmod 600) or use a secure OS credential store instead of plaintext; (4) Inspect and run the scripts in an isolated environment (virtualenv/container); (5) Remove or rotate the auth code when no longer needed. If you need the agent to auto-save credentials, only proceed if you trust the runtime environment and storage location.Like a lobster shell, security has layers — review code before you run it.
latestvk97btqpwfmvmgn5yahrcd688cn82zz66
License
MIT-0
Free to use, modify, and redistribute. No attribution required.