The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires the agent to execute shell commands using ffmpeg to encode GIF files and extract raw video frames for analysis.
[DYNAMIC_EXECUTION]: The skill utilizes python3 -c to run a script defined in the instructions for measuring loop quality. It also directs the agent to generate and execute custom animation logic in code based on user-specified movement parameters.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data which influences the code generated and executed by the agent.
Ingestion points: User-provided HTML covers and textual descriptions of movement styles and elements.
Boundary markers: Absent. The instructions do not provide delimiters or warnings to ignore instructions embedded within user-provided HTML or descriptions.
Capability inventory: Shell command execution via ffmpeg and script execution via python3.
Sanitization: Absent. There is no validation or escaping logic defined for the external content before it is processed or used in code generation.

loop-cover