The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to invoke the runcomfy CLI tool to perform video generation tasks.
Evidence: Examples such as runcomfy run wan-ai/wan-2-7/text-to-video --input '{"prompt": "<user prompt>"}' are provided in SKILL.md.
The agent is responsible for constructing these commands, incorporating user-provided prompts and URLs into a JSON input string.
[EXTERNAL_DOWNLOADS]: The skill references the installation of the RunComfy CLI from a public registry.
Evidence: npm i -g @runcomfy/cli is listed as a prerequisite in SKILL.md.
This package is the official tool for the vendor associated with this skill.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided prompts and media URLs as input for video generation, creating a surface for indirect prompt injection.
Ingestion points: User-supplied prompt and audio_url fields within the SKILL.md input schema.
Boundary markers: Input is structured as a JSON string within the CLI command: --input '{"prompt": "..."}' to prevent direct shell expansion.
Capability inventory: Execution of the runcomfy CLI as described in SKILL.md.
Sanitization: The skill documents that the CLI transmits the JSON body directly to the API without shell expansion of the prompt content.

wan-2-7