← Back to Skills Marketplace
Web fetch Google search
by
Uroboros1205
· GitHub ↗
· v1.0.0
543
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install webfetch-google
Description
Performs a web fetch request to Google based on a user-provided query. Use this skill when you need to retrieve information from Google search results.
Usage Guidance
This skill appears to do what it says: run a tiny helper that asks the agent to use its web_search tool to fetch Google results. Before installing, confirm that your agent/platform provides a web_search tool and understand how that tool sends queries (it will contact external search services). Avoid sending sensitive or private queries because they will be transmitted to an external search endpoint. Also be aware the SKILL.md contains placeholder text (TODO) and the helper script simply prints code for the agent to execute — if you need stricter auditing, inspect or run the script in a sandboxed environment and verify the platform's web_search implementation and privacy policy.
Capability Analysis
Type: OpenClaw Skill
Name: webfetch-google
Version: 1.0.0
The skill is a straightforward implementation of a Google search fetcher. The script `scripts/web_search.py` takes a user query and returns a JSON object intended to trigger an internal `web_search` tool. While the `SKILL.md` contains significant amounts of boilerplate template text, there is no evidence of malicious intent, data exfiltration, or prompt injection vulnerabilities.
Capability Assessment
Purpose & Capability
Name/description (fetch Google search results) matches the included script and SKILL.md. The skill does not request unrelated environment variables, binaries, or installs.
Instruction Scope
SKILL.md instructs running scripts/web_search.py with the user query; the script prints JSON containing a call to default_api.web_search(query=...). This is coherent for a skill that delegates searching to a platform-provided tool, but it implicitly depends on the agent exposing a 'web_search' tool (not declared in the skill). The SKILL.md also contains template/placeholder content (TODO) but no instructions to read unrelated files or secrets.
Install Mechanism
No install spec — instruction-only with a tiny Python helper script. Nothing will be downloaded or written to disk beyond the provided script.
Credentials
No environment variables, credentials, or config paths are requested. The level of access requested is proportional to the stated purpose.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request persistent presence or modify other skills or system settings. Autonomous invocation is allowed (platform default) but not unusual here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install webfetch-google - After installation, invoke the skill by name or use
/webfetch-google - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of the webfetch-google skill.
- Allows users to fetch Google search results by providing a query.
- Executes a script to retrieve and return content from Google based on the user’s input.
Metadata
Frequently Asked Questions
What is Web fetch Google search?
Performs a web fetch request to Google based on a user-provided query. Use this skill when you need to retrieve information from Google search results. It is an AI Agent Skill for Claude Code / OpenClaw, with 543 downloads so far.
How do I install Web fetch Google search?
Run "/install webfetch-google" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Web fetch Google search free?
Yes, Web fetch Google search is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Web fetch Google search support?
Web fetch Google search is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Web fetch Google search?
It is built and maintained by Uroboros1205 (@uroboros1205); the current version is v1.0.0.
More Skills