The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill uses runpy.run_path in the Python recipe to execute scripts stored in sibling directories (e.g., stylized-style, lighting, rendering). This is a standard method for modular code execution within the agent's local environment.
[INDIRECT_PROMPT_INJECTION]: The skill ingests a target variable used to identify 3D assets to be styled.
Ingestion points: target variable used in the Python snippet within SKILL.md.
Boundary markers: No delimiters or safety instructions are used for the target input.
Capability inventory: Calls runpy.run_path to execute toon_material.py, light_rig.py, render_preset.py, and comp_grade.py.
Sanitization: No explicit sanitization of the target string before it is passed to scripts.
[METADATA_POISONING]: The YAML frontmatter lists a different author profile (arjun988) than the reported vendor. This inconsistency is common in shared or forked repositories and does not present a safety risk.

cartoon-style