Security audit
Security checks for vulnerabilities and agentic risk
This skill does what it says: it uses Tavily to crawl websites and can optionally save the returned pages locally.
Install this only if you are comfortable sending crawl URLs and instructions to Tavily using your Tavily API key. Avoid crawling sensitive internal or proprietary sites without approval, and use conservative --depth and --limit values when saving output locally.
The skill advertises and documents behavior that uses environment secrets and external network access, but it does not declare an explicit tool scope such as permissions or allowed-tools. That weakens user and platform visibility into what the skill can access and increases the chance the skill is run with broader capabilities than intended.
The authentication section explains how to provide an API key but does not warn that crawl targets, page contents, and possibly user-provided instructions are sent to the external Tavily service. This creates a data exposure risk because users may unknowingly transmit internal URLs, proprietary documentation, or sensitive content to a third party.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
console.error(`Crawling ${url} (depth: ${maxDepth}, limit: ${limit})...`);
const resp = await fetch("https://api.tavily.com/crawl", {
method: "POST",
headers: {
"Content-Type": "application/json",
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
console.error(`Crawling ${url} (depth: ${maxDepth}, limit: ${limit})...`);
const resp = await fetch("https://api.tavily.com/crawl", {
method: "POST",
headers: {
"Content-Type": "application/json",
The description says the skill can save crawled pages as local markdown files, but it does not clearly warn that using --output may create a large number of files and consume significant disk space. In an agent setting, that can lead to unintended local writes, workspace clutter, or storage exhaustion if limits are set too high.
No suspicious patterns detected.