multi-search-engine

• Outcome: Pass
• Latest audit: May 29, 2026, 8:18 PM
• Version:
  2.0.1

Overview

This skill locally builds search-engine URLs; the main risk is that opened search links send the query text to the chosen search provider.

Safe to install for generating search URLs. Avoid putting secrets, private identifiers, customer data, or confidential research terms into queries, because opening a generated search URL shares the query with that search provider.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The trigger examples are broad conversational requests that could cause over-activation of the skill in contexts where the user did not explicitly intend to invoke this URL-building capability. In agent environments, ambiguous activation boundaries can lead to unintended search URL generation, privacy leakage through external search links, or confusing tool selection behavior.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The document repeatedly includes executable-style `web_fetch` examples that send user-supplied queries to third-party search providers, but it does not warn that queries, metadata, and potentially sensitive research terms will be disclosed externally. In an agent skill context, this is more dangerous than ordinary documentation because users may copy these examples into automated workflows and unintentionally transmit confidential prompts or internal terms to external services.

VirusTotal

65/65 vendors flagged this skill as clean.