ClawHub

Web Searcher

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed web research helper that searches and fetches external pages, with no evidence of hidden installation, credential use, persistence, or destructive behavior.

Install this for tasks where live web research is appropriate. Avoid using it with sensitive private topics you would not want sent to search or fetch tools, and review cited sources before relying on important claims.

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
84% confidence
Finding
The description uses broad activation language such as 'research a topic,' 'find information,' and 'answer questions,' which could cause the skill to trigger for many generic requests. Over-broad invocation increases the chance of unnecessary web access, external data exposure, or bypass of more narrowly scoped safer skills.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill instructs the agent to fetch external pages and perform people/company research, including LinkedIn and company pages, without any user-facing notice or privacy safeguards. This creates risk of collecting or surfacing personal data from third-party sites without informed user awareness, and encourages external network access that may be unexpected in ordinary prompts.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal