Tavily AI Search

AI-optimized web search using Tavily Search API. Use when you need comprehensive web research, current events lookup, domain-specific search, or AI-generated answer summaries. Tavily is optimized for LLM consumption with clean structured results, answer generation, and raw content extraction. Best for research tasks, news queries, fact-checking, and gathering authoritative sources.

Install this only if you are comfortable sending search queries and selected options to Tavily under your API key. Avoid using it with secrets, private internal documents, regulated data, or sensitive personal information, and treat search results or URLs fetched with curl as untrusted content. Pin or review the tavily-python dependency in stricter environments.

Type: OpenClaw Skill Name: tavily Version: 1.0.0 The skill bundle provides a Python script for interacting with the Tavily search API, which appears benign and correctly handles API keys. However, the `SKILL.md` documentation includes an 'Integration Patterns' example demonstrating how to chain the search results with `jq` and `curl` to fetch raw content from URLs (`scripts/tavily_search.py "React documentation" --json | jq -r '.results[].url' | xargs -I {} curl -s {}`). While presented as a legitimate content extraction method, this example highlights the agent's capability to execute arbitrary network requests (`curl`) based on search results, which is a high-risk primitive that could be exploited by a malicious prompt to access or exfiltrate data from unintended external or internal network resources. This capability, though not explicitly malicious in its stated purpose, makes the skill suspicious due to the potential for misuse via prompt injection.