ClawHub

Conversation Video

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent video-generation helper whose command use and file output are expected for making audio and MP4 files.

Install only if you are comfortable running local media-generation commands and npm install for the optional Remotion template. Review transcript contents before use, because generated audio, timing JSON, terminal logs, and temporary WAV files may contain the spoken text.

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
90% confidence
Finding
The skill instructs the agent to invoke shell commands and write output files, but it does not declare permissions for those capabilities. This creates a permission-model mismatch: an orchestrator or reviewer may assume the skill is low-risk while it can actually execute local commands such as Python, ffmpeg, npm, and cp, potentially affecting the filesystem and triggering dependency installation or external tool execution.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal