The Agent Skills Directory

[SAFE]: The skill implements secure API key handling by utilizing environment variables or a local configuration file with restricted file permissions (chmod 600).
[EXTERNAL_DOWNLOADS]: Technical documentation and API schemas are retrieved from the vendor's official domain (pixazo.ai).
[COMMAND_EXECUTION]: The skill provides standard implementation examples using curl and established libraries to interact with the Pixazo API gateway.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text for audio generation. Ingestion points: User-provided text for the prompt parameter (SKILL.md). Boundary markers: Absent. Capability inventory: Network POST requests to gateway.pixazo.ai (SKILL.md). Sanitization: Absent. The risk is considered safe as the data is only used to populate a text field for a specific authenticated API call.

elevenlabs