The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external animation specifications and frame descriptions to generate runnable code and asset generation prompts.\n
Ingestion points: Animation manifests (manifest.json) and raw energy curves (motion.json) located in the .motiscope directory.\n
Boundary markers: The skill does not employ boundary markers or specific instructions to the agent to ignore potentially malicious instructions embedded within the animation spec data.\n
Capability inventory: The skill has access to Bash (shell execution), Write (filesystem modification), and interaction with other animation skills.\n
Sanitization: There is no evidence of sanitization or strict schema validation for the animation and effect fields before they are used in code generation.\n- [COMMAND_EXECUTION]: The skill invokes the Bash tool to execute local Python scripts (config.py and assetgen.py) used for configuration retrieval and automated asset generation.

recreate