create-movie

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: Orchestration of local skills and sandboxed code execution.
  • Executes other agent skills such as memory and create-image using bash scripts via subprocess calls in skill_registry.py.
  • Generates and executes Python scripts within a network-isolated Docker sandbox to perform custom video processing tasks as part of the build-tools phase.
  • [EXTERNAL_DOWNLOADS]: Communication with established AI service providers.
  • Interacts with Together AI, Kling AI, and Google Cloud APIs to generate and download movie assets.
  • These operations are fundamental to the skill's purpose and target well-known technology domains.
  • [PROMPT_INJECTION]: Natural language instructions for AI model guidance.
  • Employs task-specific prompts to guide LLMs in creating poetic narrations and structured screenplays.
  • Uses delimiters and role-assignment techniques to maintain model focus within the creative pipeline.
  • [SAFE]: The skill follows security best practices including environment variable usage for secrets and strict containment for dynamic code execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 06:35 AM
Security Audit — agent-trust-hub — create-movie