skills/pixazo-ai/skills/mai-image/Gen Agent Trust Hub

mai-image

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides implementation examples using curl for making POST requests to the Pixazo API gateway (gateway.pixazo.ai).
  • [EXTERNAL_DOWNLOADS]: Instructions include fetching extended documentation and model schemas from the vendor's official domain (pixazo.ai).
  • [CREDENTIALS_UNSAFE]: The skill manages a PIXAZO_API_KEY. It follows local security best practices by instructing the agent to store the key in ~/.pixazo/api-key with restricted file permissions (chmod 600).
  • [COMMAND_EXECUTION]: The skill references a command (npx skills add Pixazo-AI/skills) for managing related components from the vendor's package repository.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text for the prompt field in image generation requests. While it does not utilize explicit boundary markers in the code snippets, the impact is limited to the generation of image assets based on user input.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 09:01 PM