QQBrowserSkill
v0.7.4Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking...
⭐ 4· 476·3 current·3 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 (browser automation) align with the runtime instructions: commands to navigate pages, click, fill forms, take screenshots, and download files. The requested permissions (network, filesystem temporary directories) are expected for a browser automation tool.
Instruction Scope
SKILL.md confines actions to browser operations and temporary file storage, and the command examples operate only on web pages and snapshots. There are no instructions to read unrelated system files or to access environment variables beyond the tool's runtime needs. The instructions appropriately warn about token consumption for snapshot calls.
Install Mechanism
The skill is instruction-only in the registry (no enforced install spec), but the README tells users to pipx/pip install the PyPI package and then run `qqbrowser-skill install`, which downloads a QQ Browser package from Tencent's CDN (dldir1v6.qq.com) over HTTPS. Downloading and extracting a browser binary is expected for this functionality, but it does involve running a third-party binary downloaded at install time — verify trust in the PyPI package and the downloaded payload before installing on sensitive hosts.
Credentials
No environment variables, credentials, or unrelated service keys are requested. The permission model is limited to outbound network and temporary filesystem use, which are proportionate to a browser automation skill.
Persistence & Privilege
The skill is not forced-always, does not request system-wide configuration changes, and does not declare elevated persistence. Autonomous invocation is allowed (platform default) but is not combined with other concerning flags.
Assessment
This skill appears coherent for browser automation: it will need outbound network access and will download and install a browser binary (via the qqbrowser-skill install command) and save screenshots/downloads to temporary directories. Before installing, review the PyPI package (qqbrowser-skill) source and package contents, confirm you trust the Tencent CDN/download, and consider running it inside an isolated environment (VM/container) if you are concerned about executing third-party binaries. Be mindful that browser automation can interact with authenticated pages and could expose data you navigate to — avoid pointing it at sensitive accounts or secrets unless you trust and vet the package.Like a lobster shell, security has layers — review code before you run it.
latestvk979se0fhnqvr26tjh3m2jgbbn83gevb
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
