ClawHub

Skill Exporter

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward exporter that generates service files from a user-chosen skill, with deployment hardening left to the user.

Install this only if you want a local code generator for turning trusted skills into services. Before deploying generated output, review copied scripts, add authentication and rate limits, restrict CORS, store API keys in deployment secrets, and pin dependencies for production builds.

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
91% confidence
Finding
The skill documentation describes capabilities that imply reading/writing files, invoking Python scripts, and generating deployable services, but it does not declare any permissions. This creates a transparency and policy-enforcement gap: an agent or reviewer may approve the skill without understanding that it can access the filesystem, environment variables, shell, and network during export and deployment workflows.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal