The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the user to install an external tool, rawgenai, from the author's Homebrew tap (WHQ25/tap/rawgenai). This involves downloading and executing a third-party package manager formula.
[COMMAND_EXECUTION]: The skill's primary functionality is delivered through the execution of shell commands using the rawgenai CLI. This tool is used for configuration, video generation, status checking, and downloading results.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text and external media files, creating a surface for potential prompt injection.
Ingestion points: User-provided text prompts and file paths for images or videos are ingested via command-line arguments in SKILL.md and provider-specific reference files (e.g., references/video/openai.md, references/video/google.md).
Boundary markers: The instructions do not specify any delimiters or warnings to ignore instructions embedded within the processed media or prompts.
Capability inventory: The skill has the capability to execute shell commands (rawgenai) as documented in SKILL.md and across all files in the references/video/ directory.
Sanitization: There is no mention of input sanitization, validation, or escaping for the prompts or file inputs before they are passed to the CLI tool.

agent-gen-video