AIsa Tavily

Security checks across malware telemetry and agentic risk

Overview

This is a small AIsa web-research skill whose main risk is that searches, URLs, and the AIsa API key are sent to AIsa's hosted API.

Install this only if you trust AIsa/api.aisa.one with the queries and URLs you submit. Use a scoped or rotatable AISA_API_KEY where possible, and avoid sending secrets, private URLs, regulated data, or internal-only research topics unless your organization approves that use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The setup notes that an API key is required for AIsa-backed access, but it does not clearly disclose that user queries and possibly attached context will be transmitted to an external third-party service. This can lead to inadvertent sharing of sensitive prompts, proprietary research topics, or internal data under the mistaken assumption that processing is local.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal