The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to store a user-provided API key in ~/.pixazo/api-key and apply chmod 600 to the file. This is a recommended security practice to ensure that sensitive credentials are only readable by the owner.
[EXTERNAL_DOWNLOADS]: The agent is directed to fetch operational specifications and parameter schemas from the vendor's official domain at https://www.pixazo.ai/models/omnihuman.md. These resources are provided by the author of the skill to ensure compatibility with the API.
[INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface where it reads external model specifications from a remote markdown file.
Ingestion points: External model configuration fetched from https://www.pixazo.ai/models/omnihuman.md.
Boundary markers: None explicitly defined in the fetch instructions.
Capability inventory: Network requests via curl, Python requests, and JavaScript fetch; file creation and permission modification (chmod) for the API key file.
Sanitization: No specific sanitization or filtering is described for the content retrieved from the model specification URL.

omnihuman