Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward Tavily web-search wrapper that sends user-provided searches to Tavily and does not show hidden persistence, privilege escalation, or unrelated data access.
Install only if you are comfortable sending search terms and selected search options to Tavily. Avoid using confidential prompts, secrets, personal data, or proprietary internal identifiers as search queries unless Tavily's data handling terms meet your needs.
The skill requires environment access for TAVILY_API_KEY and performs outbound web/API requests, but the manifest does not declare an explicit tool scope such as permissions or allowed-tools. This weakens least-privilege controls and makes the skill's actual capabilities less transparent to operators reviewing whether it can access secrets or send data off-box.
The documentation explains how to run searches but does not clearly warn that user queries are transmitted to Tavily's external API, and options like --raw-content may increase the amount of third-party data returned and handled. In a skill that brokers web search, this omission can lead users or upstream agents to unknowingly send sensitive prompts, internal identifiers, or proprietary research terms to an external service.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
if (includeDomains.length > 0) body.include_domains = includeDomains;
if (excludeDomains.length > 0) body.exclude_domains = excludeDomains;
const resp = await fetch("https://api.tavily.com/search", {
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.
if (includeDomains.length > 0) body.include_domains = includeDomains;
if (excludeDomains.length > 0) body.exclude_domains = excludeDomains;
const resp = await fetch("https://api.tavily.com/search", {
method: "POST",
headers: {
"Content-Type": "application/json",
No suspicious patterns detected.