Security audit

Web Search Instant

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a straightforward DuckDuckGo web search helper, with the main caveat that search terms are sent to an external service.

Install only if you are comfortable with search queries being sent to DuckDuckGo. Avoid using it for secrets, credentials, private incident details, proprietary names, or other sensitive text, and prefer explicit web-search requests to avoid accidental activation.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (2)

Vague Triggers

Medium

Confidence: 86% confidence
Finding: The trigger phrases are extremely broad, including common conversational patterns like 'what is', 'how to', 'find information', and 'google something', which can cause this skill to activate in many unrelated contexts. Overbroad activation increases the chance of unintended network requests, data leakage through user prompts being sent externally, and tool overuse where a less-privileged response would have sufficed.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The script sends the user's raw search query to DuckDuckGo's external API without clearly warning the user at execution time that their input will leave the local environment. In an agent-skill context, users may include sensitive internal data, credentials, incident details, or proprietary terms in a query, causing unintended disclosure to a third party.

VirusTotal

56/56 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.