jhjhghg
/install anhfabh1-test
ClawSentry
Use Cases
- Use this skill when you need to install and prepare the
ai-assistant-security-openclawplugins for the OpenClaw environment on the current machine. - Trigger this skill when the user mentions requirements such as "install clawSentry / ai-assistant-security-openclaw plugin / 帮我安装clawSentry技能 / 安装clawSentry技能".
Steps
1. Verify Node.js is installed:
Ensure Node.js (version 14 or higher) is installed on the system. You can check with:
node --version
2. Execute the combined script to install plugin and generate login link:
node {baseDir}/scripts/bundle.cjs
After the script completes:
- The script will display the login URL directly. You can also extract it from the output by looking for the line that starts with
[LOGIN_URL]: - You can also read the login URL from
{baseDir}/.state/login_state.jsonfile (look for theloginUrlfield). If the file doesn't exist, try reading it again after a few seconds. If you can't find the files, try looking in.openclaw/skills/ClawSentry/scripts/directory. - Send the login URL to the user along with this message: "After completing login, if you want to check if the installation was successful, please wait one minute and then ask me such as 'view all plugin list / 查看我的本地插件 '"
Data & Privacy
- The script generates a per-machine device identifier locally, then sends only its SHA-256 hash as
X-Ai-Device-Fingerprintfor device-binding of the login session. - The script does not collect or transmit MAC addresses, hostname, or other hardware identifiers.
- The script persists login state under
{baseDir}/.state/, includingloginToken, the hasheddeviceFingerprint, expiry metadata, and login progress flags. - The polling log written to
{baseDir}/.state/poll_login.logrecords operational output and API responses; once authorization succeeds, those responses may include credential material such asApiKeyandAppId. - After authorization, the script writes the received
ApiKeyandAppIdinto the local OpenClaw plugin configuration so the installed plugin can call the remote service. - That configuration update is performed by invoking the local
openclawCLI with a JSON payload, so credential values may be exposed transiently in local process arguments or shell/audit tooling on the host.
Network Targets
- The script performs HTTPS requests to the API base URL embedded in the bundle at build time (
internalConfig.baseURL) to create a login token and check login status. - The login URL shown to the user is generated using the embedded console URL prefix (
internalConfig.baseLogUrl).
Local Files
{baseDir}/.state/login_state.json: StoresloginUrl,loginToken,deviceFingerprint(hashed), expiry metadata, and login progress flags.{baseDir}/.state/poll_login.log: Stores polling logs for troubleshooting, including request/response-related output from the login-status flow.{baseDir}/.state/device_id: Stores the locally generated device identifier used to derive the fingerprint hash.
Host Changes
- The script runs
openclawCLI commands to install the plugin, read and update local OpenClaw plugin configuration, and restartopenclaw gatewayon the machine.
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install anhfabh1-test - After installation, invoke the skill by name or use
/anhfabh1-test - Provide required inputs per the skill's parameter spec and get structured output
What is jhjhghg?
Install and configure the security-related plugins required by OpenClaw, including the `ai-assistant-security-openclaw` plugins. Use this skill when you want... It is an AI Agent Skill for Claude Code / OpenClaw, with 105 downloads so far.
How do I install jhjhghg?
Run "/install anhfabh1-test" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is jhjhghg free?
Yes, jhjhghg is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does jhjhghg support?
jhjhghg is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created jhjhghg?
It is built and maintained by qinjianfenghzau-wq (@qinjianfenghzau-wq); the current version is v1.0.9.