← Back to Skills Marketplace
513
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install phone-agent-skill
Description
Use AI AutoGLM Phone Agent for automated mobile device control. Suitable for tasks requiring mobile phone automation, such as APP automated testing, data col...
Usage Guidance
This skill appears to do what it says (drive an Android device through a local AutoGLM Phone Agent), but its registry metadata omits important runtime requirements. Before installing or invoking it:
- Treat it as able to perform ANY UI action on a connected device. Use only test devices/accounts and never a personal device with sensitive data.
- The SKILL.md expects adb in PATH and an env var PHONE_AGENT_ENDPOINT pointing at a locally running Phone Agent service—ask the publisher to add these to the declared requirements, or set them manually in a controlled environment.
- Verify the AutoGLM Phone Agent SDK you install is from a trusted source (the README points to https://github.com/zai-org/Open-AutoGLM; confirm repository authenticity and review its code).
- Run the SDK and test commands manually (adb devices, curl the endpoint) before letting the agent invoke the skill autonomously.
- Be careful granting overlay/accessibility permissions on devices; those permissions allow broad UI control and can be abused.
If the publisher cannot or will not update the metadata to list required binaries and the PHONE_AGENT_ENDPOINT env var, treat the omission as a red flag and prefer manual, sandboxed testing only.
Capability Analysis
Type: OpenClaw Skill
Name: phone-agent-skill
Version: 1.0.0
The skill provides extensive control over an Android device (tap, type, swipe, launch apps, screenshots, read UI text) via a user-configured `PHONE_AGENT_ENDPOINT`. While the `SKILL.md` instructions themselves do not contain explicit malicious commands or prompt injection attempts, the inherent capability for automated mobile device control is high-risk. The reliance on a user-defined local endpoint (`PHONE_AGENT_ENDPOINT`) could become a vulnerability if misconfigured to point to a malicious external service or if the local service itself is compromised, allowing potential unauthorized actions or data exfiltration through the agent's capabilities.
Capability Assessment
Purpose & Capability
The SKILL.md describes legitimate mobile automation capabilities (tap, swipe, screenshots) consistent with the stated purpose. However, the registry metadata declares no required binaries or env vars while the instructions explicitly require adb in PATH, the AutoGLM Phone Agent SDK, and an endpoint exposure (PHONE_AGENT_ENDPOINT). The mismatch between declared requirements and actual runtime needs is a material incoherence.
Instruction Scope
The instructions stay inside the stated domain: they direct the agent to interact with an AutoGLM Phone Agent backend and an Android device via adb and the SDK. They do not instruct the agent to read unrelated host files or secrets. They do, however, require the agent to be able to reach a local HTTP service and to perform real UI actions on a connected device, which is expected for this skill but carries device-level risk.
Install Mechanism
This is an instruction-only skill with no install spec or code files, which reduces filesystem/install risk. The SKILL.md references installing an external SDK and running its agent, but the skill itself does not pull or install code — the user/administrator must install the SDK separately.
Credentials
The runtime instructions require environment configuration (PHONE_AGENT_ENDPOINT) and adb availability, but these are not declared in the skill metadata (requires.env and required binaries are empty). While the skill does not request cloud credentials or secrets, it does ask the operator to grant overlay/accessibility permissions on devices — appropriate for automation but sensitive. The missing declarations reduce transparency about what the skill will need access to.
Persistence & Privilege
The skill does not request always:true and does not modify other skills or global agent settings. Model invocation is allowed (default), which is normal for skills that perform actions; combined with the ability to control a device this increases blast radius but is expected for an automation skill.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install phone-agent-skill - After installation, invoke the skill by name or use
/phone-agent-skill - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of AutoGLM Phone Agent skill.
- Enables natural language control of Android devices via the AutoGLM Phone Agent SDK.
- Supports actions such as tapping, swiping, typing, launching apps, taking screenshots, and reading UI text.
- Includes detailed prerequisite, setup, and usage instructions.
- Provides troubleshooting guidance and safety best practices.
- Designed for mobile automation tasks like app testing, UI interaction, and data collection.
Metadata
Frequently Asked Questions
What is Phone agent?
Use AI AutoGLM Phone Agent for automated mobile device control. Suitable for tasks requiring mobile phone automation, such as APP automated testing, data col... It is an AI Agent Skill for Claude Code / OpenClaw, with 513 downloads so far.
How do I install Phone agent?
Run "/install phone-agent-skill" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Phone agent free?
Yes, Phone agent is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Phone agent support?
Phone agent is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Phone agent?
It is built and maintained by gaojizhou (@gaojizhou); the current version is v1.0.0.
More Skills