The Agent Skills Directory

[COMMAND_EXECUTION]: The skill documents how to automate 3ds Max using command-line arguments, including execution of the primary binary (3dsmax.exe) with scripts and rendering parameters.
[DYNAMIC_EXECUTION]: The skill demonstrates dynamic loading and execution of MAXScript files using the fileIn command and automated scene loading via loadMaxFile within loop structures.
[INDIRECT_PROMPT_INJECTION]: The skill describes patterns for reading data from external sources, such as JSON configuration files and existing scene files, which represents a potential attack surface for indirect prompt injection.
Ingestion points: The readJSON function and processAllScenes loop in SKILL.md are used to read and process external file data.
Boundary markers: The code does not implement specific boundary markers or instructions to ignore embedded prompts within the external data.
Capability inventory: The skill includes scripts that can write to the local file system (log creation and file exporting) and execute shell commands.
Sanitization: The provided examples do not include sanitization or validation logic for data ingested from external file paths or JSON fields.

3dsmax-scripting