ClawHub
Back to skill

Security audit

firstdata

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed connector to a hosted FirstData lookup service, with the main caution being careful handling of the API token and off-platform queries.

Install only if you trust the FirstData hosted service. Treat FIRSTDATA_API_KEY like a password, avoid sending secrets or regulated data through the MCP unless approved, prefer manual configuration or a pinned CLI version, and rotate the token if it is exposed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs users to connect to a third-party hosted MCP endpoint and send an Authorization bearer token, but it does not clearly warn that user queries and authentication data will be transmitted off-platform to a remote service. This creates a real privacy and credential-handling risk because users or agents may disclose sensitive prompts, research topics, or secrets without informed consent.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.