The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to manage a local configuration file for authentication.
It suggests storing the API key at ~/.pixazo/api-key and explicitly recommends using chmod 600 to restrict file access to the current user, which is a security best practice for secret management.
It mentions the npx command for installing additional related skills from the vendor's GitHub repository.
[EXTERNAL_DOWNLOADS]: The skill references external resources for documentation and extended functionality.
It points to https://www.pixazo.ai/models/glm-image.md for full model references and schemas.
All network operations, including the API gateway (gateway.pixazo.ai) and the console (api-console.pixazo.ai), belong to the skill vendor's own infrastructure.
[INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted external data.
Ingestion points: The agent accepts text prompts and reference image data (URLs or base64) from users to build API requests (found in SKILL.md).
Boundary markers: The skill does not define specific delimiters for these inputs but provides a structured JSON template for the API call.
Capability inventory: Capabilities are limited to making network POST requests to a specific vendor-owned gateway using curl, requests, or fetch.
Sanitization: The skill utilizes an enable_safety_checker parameter in the API request to mitigate the generation of unsafe content.

glm-image