Groundapi Web Researcher

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed GroundAPI web-research skill with a mild risk of triggering on broad research or summary requests.

Install only if you are comfortable sending research topics, search queries, and scraped URLs through GroundAPI. Use a revocable API key and avoid sensitive private topics or internal-only URLs unless you intentionally want external research.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger phrases are very broad and match common requests like 'help me look up' or 'summarize this topic,' which can cause the skill to auto-activate outside the user's specific intent to use this tool. In an agent environment, overbroad activation increases the chance of unnecessary external searches and scraping, creating privacy, consent, and tool-misuse risks.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal