ClawHub
Back to skill

Security audit

Mentions Discover

Security checks across malware telemetry and agentic risk

Overview

This skill is a narrowly scoped MentionsAPI helper that uses a disclosed API key to send brand query-discovery requests to a fixed external API.

Install only if you trust MentionsAPI and are comfortable storing MENTIONSAPI_KEY locally. Each discover_queries call is documented as costing $0.50, so confirm the brand and count before use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill documentation indicates access to sensitive environment data (`MENTIONSAPI_KEY`) and external network interaction, but it does not declare explicit permissions. This creates a transparency and policy-enforcement gap: a host may expose credentials or allow outbound requests without users and orchestrators having a clear, machine-readable permission model to review or restrict.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.