Web Search Pro

PassAudited by ClawScan on May 10, 2026.

Overview

This appears to be a legitimate web search and crawling skill, but it sends queries/URLs to external providers, can use optional API keys, and keeps a local cache.

Install if you want an agent to perform live web search, extraction, and bounded crawling. Before using it, decide which external providers you trust, configure only the API keys you need, be aware that queries and URLs may be sent to those services, and clear the local cache if you search or retrieve sensitive material.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

The agent can make outbound web requests and may visit multiple pages when asked to crawl a site.

Why it was flagged

The skill can fetch and crawl user-provided websites, including an option to allow cross-origin discovery, but the command exposes limits such as depth and maximum pages.

Skill content
crawl.mjs "url1" ["url2" ...] [options] ... --depth <n> ... --max-pages <n> ... --no-same-origin
Recommendation

Use explicit URLs, keep crawl limits small, and avoid enabling cross-origin crawling unless you intend wider discovery.

What this means

If you configure provider API keys, the skill can spend quota and send your search/extraction requests to those providers.

Why it was flagged

The engine reads a provider API key from the environment and sends it to the provider API, which is expected for authenticated search integration.

Skill content
const apiKey = (process.env.EXA_API_KEY ?? "").trim(); ... "x-api-key": apiKey
Recommendation

Use provider keys with the minimum needed scope, monitor quota/billing, and only configure providers you trust.

What this means

Search results, crawled content, or query-related data may persist locally and be reused until the cache expires or is cleared.

Why it was flagged

The skill discloses persistent local state for cached search/crawl results, which may include prior queries or retrieved page content.

Skill content
local state directory: `.cache/web-search-pro`
Recommendation

Avoid searching highly sensitive terms if local caching is a concern, and use the provided cache clear command when needed.