Nansen Web Fetcher

v0.1.0

Fetch and analyze content from one or more URLs using AI (Gemini 2.5 Flash). Use when you have specific URLs and need to extract or summarize their content....

0· 167·2 current·2 all-time
byNansen AI@nansen-devops

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for nansen-devops/nansen-web-fetcher.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Nansen Web Fetcher" (nansen-devops/nansen-web-fetcher) from ClawHub.
Skill page: https://clawhub.ai/nansen-devops/nansen-web-fetcher
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Required env vars: NANSEN_API_KEY
Required binaries: nansen
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install nansen-web-fetcher

ClawHub CLI

Package manager switcher

npx clawhub@latest install nansen-web-fetcher
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name and description (fetch and analyze web URLs) match the declared requirements: the nansen binary and NANSEN_API_KEY are exactly what the nansen CLI would need to perform web fetches and AI analysis.
Instruction Scope
SKILL.md instructs only running the nansen CLI (nansen web fetch ...) against user-supplied URLs and asking a question. It does not instruct reading unrelated files, accessing other env vars, or posting data to unexpected endpoints.
Install Mechanism
Install uses a public package manager (node/npm) installing package 'nansen-cli' which produces the nansen binary — this is expected for a CLI-based skill. This is moderate-risk compared with instruction-only skills because it writes a binary to disk; verify the npm package's authenticity and maintainers before installing.
Credentials
Only NANSEN_API_KEY is required and declared as the primary credential, which is proportionate for a service-backed fetch-and-analyze tool. No additional secrets or unrelated env vars are requested.
Persistence & Privilege
always is false and the skill does not request system-wide config changes or access to other skills' credentials. Default autonomous invocation is allowed (platform normal) and not combined with other high-risk flags.
Assessment
This skill appears to do exactly what it says: run the nansen CLI against URLs using your NANSEN_API_KEY. Before installing, verify the npm package 'nansen-cli' is the official/expected package (check the package owner, repo URL, and recent versions), consider installing in a controlled environment, and ensure the API key you provide has appropriate scope and billing controls (rotate the key after testing). If you are unsure about the npm package's provenance, inspect its source repository and published files (or run it in a sandbox) before granting your production API key.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

Binsnansen
EnvNANSEN_API_KEY
Primary envNANSEN_API_KEY

Install

Node
Bins: nansen
npm i -g nansen-cli
latestvk979zfk5przymm8xfynsh7788d8360w6
167downloads
0stars
1versions
Updated 1mo ago
v0.1.0
MIT-0

Web Fetch

Fetch and analyze content from one or more URLs using Gemini 2.5 Flash with URL context.

nansen web fetch https://nansen.ai --question "What products does Nansen offer?"
nansen web fetch --url https://example.com --url https://other.com --question "Compare these two sites"
nansen web fetch https://docs.uniswap.org/contracts/v4/overview --question "What changed in v4?"

Positional args and --url flags can be combined — all become URLs to fetch.

FlagValuesDefaultPurpose
--urlURLURL to fetch (repeatable for multiple URLs, up to 20)
--questionstringrequiredQuestion to answer about the URL content
--prettyflagoffHuman-readable JSON

Returns:

  • analysis — AI-generated answer to your question
  • retrieved_urls — URLs successfully fetched
  • failed_urls — URLs that could not be retrieved

Tip: Combine with web search — search first to find relevant URLs, then fetch to get full content.

# Find and analyze in two steps
nansen web search "uniswap v4 launch" --num-results 3 --fields link
nansen web fetch https://blog.uniswap.org/... --question "What are the key changes?"

Note: 30s timeout. Paywalled or bot-blocked pages may appear in failed_urls.

Comments

Loading comments...