The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions and code for the agent to execute API calls to gateway.pixazo.ai using curl, Python requests, and Node.js fetch.
[CREDENTIALS_UNSAFE]: The skill manages a PIXAZO_API_KEY by checking environment variables or a configuration file at ~/.pixazo/api-key. It correctly instructs the agent to apply chmod 600 to the file to secure the credentials.
[EXTERNAL_DOWNLOADS]: The skill references documentation at www.pixazo.ai and suggests a command to install further tools from the vendor's GitHub repository (Pixazo-AI/skills) using npx.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data which introduces a vulnerability surface. Ingestion points: User-provided text_prompt and API response URLs in SKILL.md. Boundary markers: None identified. Capability inventory: Network requests (curl, requests, fetch) and file writing to the user's home directory. Sanitization: None specified for the text inputs.

seed-audio