Security audit
Security checks for vulnerabilities and agentic risk
This is a straightforward Tavily web search and URL extraction skill, with the main caveat that queries, URLs, and the Tavily API key are sent to Tavily.
Install only if you are comfortable sending search queries and submitted URLs to Tavily along with your Tavily API key. Avoid using it for secrets, private internal URLs, regulated data, or sensitive research terms unless Tavily is approved for that use in your environment.
The skill advertises executable behavior that uses environment variables and network access, but it does not declare any explicit tool scope or permissions boundary. This creates a transparency and governance gap: users or orchestrators may invoke a network-capable skill without clear policy constraints, increasing the chance of unintended external requests or secret-dependent execution.
The skill description and usage text do not clearly warn that user-supplied search queries and URLs are transmitted to Tavily, an external third-party service. This can lead to accidental disclosure of sensitive prompts, internal URLs, or proprietary research targets when users assume processing is local.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
process.exit(1);
}
const resp = await fetch("https://api.tavily.com/extract", {
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.
process.exit(1);
}
const resp = await fetch("https://api.tavily.com/extract", {
method: "POST",
headers: {
"Content-Type": "application/json",
The manifest describes a skill for 'web search with structured summarization,' but this file calls Tavily's /extract endpoint and prints raw_content directly. There is no search operation or summarization logic here, so the implemented behavior is materially broader/different from the described summarization-focused purpose.
This code posts user-supplied URLs and the TAVILY_API_KEY to the external Tavily API, which is a safety-relevant data transmission. The script includes usage and missing-key errors, but it does not disclose that provided URLs and credentials will be transmitted to a third-party service.
The script sends the user's search query and the API key to Tavily's external API, but provides no user-facing disclosure or consent prompt before transmitting potentially sensitive input. In an agent skill context, users may not realize their prompts or embedded secrets are leaving the local environment, which creates privacy and data-handling risk even though the transmission is core to the feature.
The hardcoded Tavily endpoint confirms that this skill transmits data to an external service. The issue is not the specific domain itself but that the skill's behavior can move user-supplied content and credentials outside the local trust boundary, which is significant in security-sensitive or privacy-sensitive deployments.
body.days = days;
}
const resp = await fetch("https://api.tavily.com/search", {
method: "POST",
headers: {
"Content-Type": "application/json",
The hardcoded Tavily endpoint confirms that this skill transmits data to an external service. The issue is not the specific domain itself but that the skill's behavior can move user-supplied content and credentials outside the local trust boundary, which is significant in security-sensitive or privacy-sensitive deployments.
body.days = days;
}
const resp = await fetch("https://api.tavily.com/search", {
method: "POST",
headers: {
"Content-Type": "application/json",
No suspicious patterns detected.