Nansen Web Searcher

Search the web for one or more queries in parallel. Use when you need current information, news, prices, or any web content to complement on-chain Nansen data.

Security Scan

The skill is mostly coherent (it calls a nansen CLI and only requests a NANSEN_API_KEY), but the SKILL.md claims it uses the Serper API while no Serper credential is requested — this mismatch and the npm install dependency warrant caution.

Purpose & Capability

Name/description match the declared requirements: the skill requires the 'nansen' CLI and a NANSEN_API_KEY, which is appropriate for a Nansen web-search helper. However, the SKILL.md explicitly says 'Search the web ... via the Serper API' while the declared primary credential is NANSEN_API_KEY (no SERPER_API_KEY or equivalent). This is an inconsistency in documentation vs. declared requirements and could be a simple doc error or indicate the CLI uses a different upstream service requiring an additional key.

Instruction Scope

Instructions are narrow: they show CLI invocations (nansen web search ...) and do not instruct reading arbitrary files or extra environment variables. They do reference excluded domains and an alternate 'nansen web fetch' command, but there are no instructions that access unrelated system state. The Serper mention in the text is the only notable oddity.

Install Mechanism

Install spec is a node package (nansen-cli) that creates a 'nansen' binary. Installing from npm is common but carries supply-chain risk (moderate). The spec does not point to an audited release host or a pinned version; verify the package source and maintainership before installing.

Credentials

Only NANSEN_API_KEY is required and it fits the described purpose. The documentation's reference to the Serper API raises the question of whether a second API key should be required; absence of a SERPER_API_KEY declaration is unexplained and should be clarified.

Persistence & Privilege

The skill is not always-enabled and does not request system-wide persistence. It appears to be user-invocable only and does not modify other skills or configurations.

What to consider before installing

This skill appears coherent overall but has one unexplained mismatch: SKILL.md says searches use the Serper API while the skill only requests a NANSEN_API_KEY. Before installing, confirm the official source of the 'nansen-cli' npm package (maintainer, repository link, and version). Check the package code or docs to see whether it actually calls Serper (and therefore needs a SERPER_API_KEY) or whether the SKILL.md contains a copy/paste error. Treat npm installs as moderate supply-chain risk—prefer installing only from an official Nansen source or pinned release, and restrict the NANSEN_API_KEY permissions if possible. If you cannot verify the package origin, consider not installing or running it in an isolated environment. If you want, I can try to locate the nansen-cli package metadata or repository to help verify its source and whether additional credentials are required.

Web Search

Search the web for one or more queries in parallel via the Serper API.

nansen web search "bitcoin price"
nansen web search "solana ecosystem news" --num-results 5
nansen web search --query "ethereum ETF" --query "bitcoin ETF" --num-results 3

Positional args and --query flags can be combined — all become queries.

Flag	Values	Default	Purpose
--query	string	—	Query string (repeatable for multiple queries)
--num-results	1–20	10	Results per query
--pretty	flag	off	Human-readable JSON

Returns results[] — one entry per query, each with organic[] (title, link, snippet, date) and optional knowledge_graph.

Note: Some domains are excluded from results (paywalled/unfetchable sites like bloomberg.com, twitter.com). Use nansen web fetch to retrieve content from specific URLs.