ClawHub

Global Skills Search

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward skill-search tool that sends search terms to a disclosed external search API and does not show hidden file access, persistence, credentials, or destructive behavior.

Install only if you are comfortable sending skill-search queries to the publisher-operated search service. Do not include secrets, customer data, or personal information in queries, and independently review any third-party skills returned by the search before using or installing them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill documentation explicitly states that user search queries are sent to an external API, but the skill declares no corresponding permissions despite requiring Python scripts that perform network access. This creates a transparency and consent problem: users and hosting platforms may assume the skill is local-only while it actually exfiltrates input to a remote service, which is especially risky if users include secrets, internal project names, or sensitive prompts in queries.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The script sends the user's raw search query to a third-party remote API, but provides no disclosure, consent prompt, or warning that input leaves the local environment. This can expose sensitive terms, internal project names, credentials pasted by mistake, or proprietary intent to an external service and its logs, which is a real privacy and data-handling risk even though the code is otherwise straightforward.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal