ClawHub
Back to skill

Security audit

FTTR Operator Copilot

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed FTTRAI operator API tool that uses a sensitive operator token and can mark alerts read, but its access and state-changing actions match its stated purpose.

Install only for agents that should access FTTRAI operator data. Use a least-privileged operator token, keep the default trusted HTTPS RPC endpoint unless you control the replacement, and require explicit confirmation before marking alerts as read or issuing real-time device query commands.

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
96% confidence
Finding
The skill declares powerful capabilities via metadata and documented runtime behavior: it requires an auth token from the environment and makes outbound RPC calls to a cloud API, including state-changing operations and real-time device commands. If the platform relies on explicit permission declarations for user awareness, policy enforcement, or sandboxing, omitting declared permissions can cause under-scoped review and unintended access to sensitive networked operations.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.