ClawHub
Back to skill

Security audit

Web Search Hub

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward DuckDuckGo web-search helper with disclosed network searches and optional saved result files.

Install dependencies only from trusted sources, preferably in a virtual environment. Treat search queries as information sent to an external search provider, and use --output only with intended file paths to avoid overwriting files or saving sensitive research topics unintentionally.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill documents the ability to write search results to arbitrary local files via `--output`, but no corresponding permission declaration is present. Undeclared file-write capability is risky because an agent may save data to unexpected paths, overwrite user files, or persist sensitive query results without clear user awareness or policy enforcement.

Tp4

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding
The documented behavior does not accurately match what the skill instructs an agent to do: it claims a dependency on OpenClawCLI while actually relying on `duckduckgo-search`, and it omits important behaviors like arbitrary file output and richer CLI functionality. This mismatch is dangerous because security controls, reviewers, and users may make trust decisions based on incomplete or inaccurate descriptions, leading to unexpected external data transmission and local file writes.

Vague Triggers

Medium
Confidence
80% confidence
Finding
The trigger language is broad enough to activate on many generic information-seeking prompts, which can cause the skill to run in situations where a simpler built-in tool or no external lookup would be safer. Over-broad activation increases the chance of unnecessary query exfiltration to external services and unintended file creation during ordinary conversations.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill description does not prominently warn that user queries are sent to an external search provider and that results may be written to local files. This lack of disclosure creates a privacy and data-handling risk, especially if users include sensitive research topics, internal project names, or personally identifiable information in search queries or saved outputs.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.