The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script skills/shared/scripts/wordcount.py for quality control. This is a local platform utility used to verify script length against target durations.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data to generate scripts, which creates a potential surface for indirect prompt injection. * Ingestion points: User-supplied values for '主题' (Theme) and '核心要点' (Key Points) in the SKILL.md input section. * Boundary markers: None explicitly present to delimit user input from instructions. * Capability inventory: Ability to execute a local word count script and write generated content to the outputs/ directory. * Sanitization: No explicit sanitization, escaping, or validation of user-provided content is defined in the instructions.

video-script