ClawHub
Back to skill

Security audit

RFC lookup

Security checks across malware telemetry and agentic risk

Overview

This skill is a focused RFC lookup tool that uses expected network access and local caching for public IETF documents.

Before installing, be aware that normal use may download public RFC data and cache it locally. Only run the sync command if you want a large local mirror, and choose a dedicated mirror directory if overriding RFC_MIRROR or --mirror.

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 exposes capabilities to read environment variables, read/write files, invoke shell commands, and access the network, but it declares no permissions. That mismatch creates a trust and containment problem: an agent or reviewer may assume the skill is low-privilege while it can fetch remote content, access local mirror paths, and invoke external tools such as Python and ripgrep.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.