← Back to Skills Marketplace
1839
Downloads
2
Stars
3
Active Installs
2
Versions
Install in OpenClaw
/install serper-v
Description
Professional search (news, places, maps, reviews, scholar, patents) and bulk scraping via Serper API.
Usage Guidance
Before installing or running this skill: (1) Verify the npm package (@vinitngr/serper-v) on the npm registry and inspect its source repository or published tarball — do not install without reviewing code. (2) Avoid installing globally with --force; prefer a container or isolated environment to limit system changes. (3) Ask the author where `serperV auth` stores the API key and whether scraped data is sent off-device; check and audit any created config files. (4) If you must use it, create a dedicated (least-privilege) API key for Serper that can be revoked, and do not reuse high-privilege credentials. (5) If you need stronger assurance, request a versioned release link, source repo, or a signed package before proceeding.
Capability Analysis
Type: OpenClaw Skill
Name: serper-v
Version: 2.0.1
The skill is classified as suspicious primarily due to the `npm install -g @vinitngr/serper-v --force` command specified in `SKILL.md`. The `--force` flag can bypass dependency checks and overwrite existing files, which introduces a risk to system stability or integrity, even if there is no clear evidence of intentional malicious behavior. While the stated purpose of 'bulk scraping' is a high-risk capability, the instructions themselves do not indicate malicious intent for its use.
Capability Assessment
Purpose & Capability
The name/description (Serper-powered search and scraping) matches the CLI usage shown in SKILL.md (serperV search / scrape). Requiring an API key for the Serper service is expected — however, the skill metadata lists no primary credential or required env vars while the instructions explicitly require running `serperV auth <api_key>`, which is an inconsistency.
Instruction Scope
SKILL.md instructs the agent/user to globally install a third-party npm CLI and to run `serperV auth <api_key>`. It does not explain where the key is stored, how the CLI transmits scraped results, or whether scraped content is forwarded to external endpoints. The CLI uses bulk scraping commands (potentially high-volume web access) and the SKILL.md also recommends `--force` in installation — these broaden the runtime actions in ways not covered by the metadata.
Install Mechanism
There is no platform install spec, but SKILL.md and SETUP.md instruct a global `npm install -g @vinitngr/serper-v` (SKILL.md even uses `--force`). The package author scope (@vinitngr) and package source are unknown and there is no homepage or source link in the skill registry — installing an unsigned npm package globally can execute arbitrary code and modify the system.
Credentials
The skill metadata declares no required env vars or primary credential, yet the runtime steps require an API key (`serperV auth <api_key>`). That key may be stored on disk or injected into process env at runtime — the skill does not declare or constrain where secrets live. Requesting API keys is reasonable for this purpose, but the omission in metadata and lack of detail about credential handling is disproportionate/unexplained.
Persistence & Privilege
The skill is not flagged as always: true and is user-invocable (normal). However the installation instructions require a global npm install which gives the CLI persistent system presence and may store auth tokens on disk; that persistent footprint is not described in the skill metadata.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install serper-v - After installation, invoke the skill by name or use
/serper-v - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.0.1
- Removed six files, including source code, configuration, and test files.
- Added SETUP.md with setup or installation details.
- No user-facing feature changes documented; this update focuses on project structure cleanup.
v2.0.0
- Added detailed usage instructions, including example commands for search and scraping.
- Listed all supported types: search, places, maps, news, shopping, scholar, and patents.
- Documented advanced options: date range filtering, pagination, country and language codes.
- Provided step-by-step setup guide for installation and authentication.
Metadata
Frequently Asked Questions
What is serper-v?
Professional search (news, places, maps, reviews, scholar, patents) and bulk scraping via Serper API. It is an AI Agent Skill for Claude Code / OpenClaw, with 1839 downloads so far.
How do I install serper-v?
Run "/install serper-v" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is serper-v free?
Yes, serper-v is completely free (open-source). You can download, install and use it at no cost.
Which platforms does serper-v support?
serper-v is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created serper-v?
It is built and maintained by Vinit (@vinitngr); the current version is v2.0.1.
More Skills