The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data sources such as CSV files for measurements and SVG files for assets to generate animation code. This behavior creates a standard surface for indirect prompt injection where instructions embedded in processed data could potentially influence the agent's code generation or planning phases.
Ingestion points: Processes external data from paths like scenes/data/measurements.csv and scenes/assets/logo.svg as described in the scene architecture section of SKILL.md.
Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore instructions embedded within the datasets it processes.
Capability inventory: The agent is expected to generate Python code for the manim engine and use ffmpeg for post-processing and delivery tasks.
Sanitization: No specific sanitization or validation logic is provided for the external data files, relying on the agent's interpretation and the Manim library's handling of those formats.

manim-explainer-animation