topic-to-training-video

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill contains instructions for the assistant to offer to run claude mcp add to configure the Clueso MCP tool. This command is a system-level configuration used to install the necessary connector for the skill's functionality. It targets the official vendor endpoint at https://connect.clueso.io/mcp.
  • [EXTERNAL_DOWNLOADS]: References official Clueso domains (connect.clueso.io and help.clueso.io) for MCP tool connection and setup documentation. These resources are owned by the skill's vendor and are essential for the intended operation.
  • [PROMPT_INJECTION]: The skill ingests user-provided text such as topics and outlines to generate video scripts, creating a surface for indirect prompt injection.
  • Ingestion points: User-provided 'topic or outline' in SKILL.md.
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: Includes the ability to create projects, add clips, and generate narration via the clueso-mcp toolset.
  • Sanitization: No automated sanitization is described; however, the risk is mitigated by a mandatory human-in-the-loop checkpoint where the assistant must show the script to the user for confirmation before proceeding to video generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 09:42 AM
Security Audit — agent-trust-hub — topic-to-training-video