motion-previs-studio

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides numerous example shell commands for standard development and VFX workflows. These include using git to clone the repository, npm for dependency management and builds, and pip for installing CLI tools like seedance-cli. It also provides examples for running Blender with specific Python scripts. These commands are documented as user instructions and do not represent autonomous or malicious execution.
  • [EXTERNAL_DOWNLOADS]: The skill references downloads from the official GitHub repository for Motion Previs Studio (github.com/wassermanproductions/motion-previs-studio.git) and standard package managers. It also references well-known AI video services such as Runway and Seedance for API integration and generation tasks. These are documented in a neutral, informative context.
  • [DATA_EXFILTRATION]: While the skill mentions the use of API keys (e.g., RUNWAY_API_KEY), it correctly instructs the user to use environment variables ($RUNWAY_API_KEY) rather than hardcoding credentials, which is a security best practice.
  • [PROMPT_INJECTION]: No evidence of prompt injection or instructions to bypass safety guidelines was found. The skill remains focused on technical assistance for the specified software project.
  • [REMOTE_CODE_EXECUTION]: There are no patterns of remote code execution. External content is limited to cloning the project source code or installing verified CLI tools from public registries.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 01:51 PM
Security Audit — agent-trust-hub — motion-previs-studio