ClawHub
Back to skill

Security audit

Openclaw Aisa Web Search Tavily Hardened

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed AIsa/Tavily search and URL extraction helper, with the main risk being that queries and URLs are sent to AIsa's external API.

Install only if you are comfortable sending your search queries and requested URLs to AIsa/Tavily using your AISA_API_KEY. Use a dedicated key where possible, avoid confidential internal URLs, private network targets, signed links, or customer-specific resources, and keep the API key out of logs and shared environments.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Description-Behavior Mismatch

Medium
Confidence
84% confidence
Finding
The implementation performs URL extraction and sends full user-supplied URLs to a remote extraction endpoint, while the skill is described as a web search capability. This mismatch can cause users or agents to disclose private, internal, or sensitive URLs under the assumption they are only performing search, creating an integrity and data-handling risk through misleading capability scoping.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
User-supplied URLs are transmitted to an external API without any warning, consent prompt, or disclosure in the script output. If an agent passes confidential links, pre-signed URLs, internal service endpoints, or customer-specific resources, those identifiers are exposed to the third-party service and may be logged or processed externally.

External Transmission

Medium
Category
Data Exfiltration
Content
process.exit(1);
}

const resp = await fetch("https://api.aisa.one/apis/v1/tavily/extract", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
Confidence
88% confidence
Finding
fetch("https://api.aisa.one/apis/v1/tavily/extract", { method: "POST"

External Transmission

Medium
Category
Data Exfiltration
Content
process.exit(1);
}

const resp = await fetch("https://api.aisa.one/apis/v1/tavily/extract", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
Confidence
88% confidence
Finding
https://api.aisa.one/

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.