ClawHub
Back to skill

Security audit

Multi-Search

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed paid research-search skill that sends queries to an external gateway and does not show hidden persistence, destructive behavior, or unrelated data access.

Install only if you are comfortable sending search terms and extracted URLs to the configured research gateway and paying the listed per-call costs. Avoid using it for secrets, proprietary text, regulated personal data, or sensitive investigations unless you trust the gateway and have reviewed the billing setup.

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 advertises and demonstrates shell execution and outbound network access via `bash .../scripts/search.sh` and multiple external API endpoints, but it does not declare any explicit permissions or safety boundary for those capabilities. This creates a transparency and policy-enforcement gap: an agent or platform may invoke networked shell actions without clear consent, review, or restriction, increasing the chance of unintended external requests or command misuse.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill repeatedly instructs the agent to send user-provided queries to third-party services such as Tavily, OpenAlex, Crossref, arXiv, PubMed, PubChem, Data.gov, and a gateway, but it does not warn that user prompts may leave the local environment. That omission can expose sensitive, proprietary, or regulated user content to external providers, especially because the skill encourages broad fan-out across multiple domains.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.