The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external reference files, which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Reads content from ../../references/MOTION_GRAPHICS.md and associated design system files.
Boundary markers: The skill does not implement delimiters or instructions to ignore potential commands within these reference files.
Capability inventory: The skill has the capability to execute scripts/motion_graphics.py, use FFmpeg, and interface with other video tools.
Sanitization: No sanitization or validation logic is defined for the content of the referenced files.

motion-graphics