ClawHub
Back to skill

Security audit

Keyword Research

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward keyword research tool, but it sends entered search terms to third-party autocomplete services, including Bing by default.

Install only if you are comfortable sending the seed keywords you type to third-party search providers. Avoid entering confidential client names, unpublished products, or sensitive campaign terms, and use explicit --sources, --lang, and --region options when you need tighter control.

SkillSpector

Vulnerability Patterns
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill explicitly describes fetching real-time suggestions from multiple external services, which requires network access, yet no permissions are declared. Undeclared network capability weakens transparency and consent controls, making it harder for a host system or user to understand what external communication will occur and what data may be sent off-platform.

Tp4

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding
A description-behavior mismatch is a real security concern because it prevents informed review of what the skill actually does. If the implementation includes additional sources, expansion behavior, or export formats not clearly disclosed, reviewers and users may underestimate data flow, output volume, or unintended use cases, increasing the chance of misuse or policy bypass.

Static analysis

No suspicious patterns detected.