Web Search Tavily

Security checks across malware telemetry and agentic risk

Overview

This appears to be a straightforward web search skill that sends user-chosen searches and URLs to AIsa/Tavily when invoked.

Use this skill only for queries and URLs you are comfortable sending to AIsa/Tavily. Avoid secrets, internal-only links, personal data, or confidential investigation targets unless your organization approves that provider. Use a dedicated AISA_API_KEY where possible and verify the publisher/listing because the registry metadata and bundled _meta.json are not fully consistent.

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
94% confidence
Finding
The skill explicitly routes search queries and URL extraction requests to AIsa's external API gateway, but it does not warn users that prompts, search terms, or extracted URLs may be transmitted to a third party. In agent workflows, users may unknowingly pass sensitive internal queries, investigation targets, or private links, creating a real data exposure risk through normal use rather than a code exploit.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal