Tavily Search 1.0.0

AI-optimized web search using Tavily API providing concise, relevant results and optional deep or topic-specific queries for AI agents.

Security Scan

The skill's code, runtime instructions, and required environment variable (TAVILY_API_KEY) are coherent with its stated purpose of calling the Tavily web-search/extract API.

Purpose & Capability

Name/description match the actual behavior: the scripts call Tavily API endpoints for search and extraction. Required binary (node) and primaryEnv (TAVILY_API_KEY) are appropriate. Minor metadata inconsistency: the registry Owner ID (kn70vz3ncrgs3bztcbvkb9246d814db5) differs from the _meta.json ownerId (kn7azq5e6sw0fbwwzdpcwvvjzd7z0x4z); this may be a packaging/metadata error but does not change the skill's runtime behavior.

Instruction Scope

SKILL.md instructs only running the included node scripts with CLI args. The scripts only read command-line args and TAVILY_API_KEY, then POST to api.tavily.com; they do not read other files, credentials, or system paths.

Install Mechanism

No install spec or remote downloads; code is shipped in the package and requires an existing Node runtime. This is low-risk for installation.

Credentials

Only a single service credential (TAVILY_API_KEY) is required and is used directly by the scripts. No unrelated secrets or multiple credentials are requested.

Persistence & Privilege

Skill does not request persistent/system-wide privileges; always is false and it does not modify other skills or system config. Agent autonomous invocation remains the platform default (disable-model-invocation:false) which is expected.

Assessment

This skill appears to do what it claims: it sends your TAVILY_API_KEY and query or URL data to api.tavily.com and prints results. Before installing, consider: (1) only provide your Tavily API key if you trust the Tavily service and the publisher; the scripts send the API key in request bodies to Tavily. (2) Extracting page content will transmit that page text to Tavily — avoid using it for private/internal URLs. (3) Verify the small metadata mismatch in ownerId with the publisher if provenance is important. (4) Ensure your Node runtime is recent enough to support fetch (Node 18+), and that network access to api.tavily.com is acceptable in your environment.

Tavily Search

AI-optimized web search using Tavily API. Designed for AI agents - returns clean, relevant content.

Search

node {baseDir}/scripts/search.mjs "query"
node {baseDir}/scripts/search.mjs "query" -n 10
node {baseDir}/scripts/search.mjs "query" --deep
node {baseDir}/scripts/search.mjs "query" --topic news

Options

• -n <count>: Number of results (default: 5, max: 20)
• --deep: Use advanced search for deeper research (slower, more comprehensive)
• --topic <topic>: Search topic - general (default) or news
• --days <n>: For news topic, limit to last n days

Extract content from URL

node {baseDir}/scripts/extract.mjs "https://example.com/article"

Notes:

• Needs TAVILY_API_KEY from https://tavily.com
• Tavily is optimized for AI - returns clean, relevant snippets
• Use --deep for complex research questions
• Use --topic news for current events