Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward AIsa/Tavily web search and URL extraction wrapper that sends user-provided queries or URLs to the documented external API.
Install only if you are comfortable sending search queries and submitted URLs to AIsa's API using your AISA_API_KEY. Do not use it for confidential prompts, private documents, presigned URLs, or internal-only links unless AIsa is approved for that data.
The skill invokes Node scripts that require both environment-variable access (AISA_API_KEY) and outbound network access, but the manifest does not declare an explicit tool scope such as permissions or allowed-tools. This creates a governance gap: a host may grant broader capabilities than intended, making it harder to enforce least privilege or audit what the skill is allowed to do.
The script accepts arbitrary user-supplied URLs and forwards them to a remote extraction service, enabling retrieval of content far beyond a narrow web-search function. In an agent context, this broader capability can be abused to fetch internal documentation links, pre-signed URLs, or other sensitive resources if such URLs are ever exposed to the agent.
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.aisa.one/apis/v1/tavily/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.aisa.one/apis/v1/tavily/extract", {
method: "POST",
headers: {
"Content-Type": "application/json",
The script performs arbitrary page content extraction from provided URLs, which is materially broader than the stated manifest description of AI-oriented web search. This mismatch can mislead users and downstream policy systems about the data-access scope, increasing the risk of unexpected retrieval of sensitive or proprietary page contents.
This code performs an outbound HTTPS request to an external service and includes the user's query in the JSON body along with a bearer token. In an agent skill context, that creates a real data exfiltration boundary: any sensitive input supplied to the tool is transmitted to a remote operator outside the local trust boundary.
body.days = days;
}
const resp = await fetch("https://api.aisa.one/apis/v1/tavily/search", {
method: "POST",
headers: {
"Content-Type": "application/json",
This code performs an outbound HTTPS request to an external service and includes the user's query in the JSON body along with a bearer token. In an agent skill context, that creates a real data exfiltration boundary: any sensitive input supplied to the tool is transmitted to a remote operator outside the local trust boundary.
body.days = days;
}
const resp = await fetch("https://api.aisa.one/apis/v1/tavily/search", {
method: "POST",
headers: {
"Content-Type": "application/json",
The script sends the user-provided query to an external third-party endpoint without any explicit disclosure, confirmation, or warning at runtime. This can expose sensitive prompts, internal data, or personal information if users assume the search is local or do not realize their input is being transmitted off-host.
No suspicious patterns detected.