ClawHub
Back to skill

Security audit

Byted Mediakit Shared

Security checks across malware telemetry and agentic risk

Overview

This skill is a documented MediaKit CLI helper with expected cloud, credential, and local file behaviors, but users should handle API keys and sensitive media carefully.

Install only if you trust the MediaKit CLI package and service. Prefer environment variables, the interactive init flow, or a secure config path for API keys instead of putting real keys on the command line, and use local mode for sensitive media unless you intend to upload it for cloud processing.

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
93% confidence
Finding
The skill includes non-interactive initialization examples that pass the API key directly on the command line (`--api-key <key>`). Even with a placeholder, this teaches and normalizes an unsafe pattern because real usage can expose secrets through shell history, process listings, audit logs, or agent/tool traces in shared environments. In a shell-permitted agent skill, that risk is more significant because commands may be logged automatically by the host runtime.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.