muapi-chibi-collage-effect

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes muapi CLI commands (muapi image edit, muapi predict wait, muapi auth configure) to interact with the underlying image generation service.
  • [EXTERNAL_DOWNLOADS]: It makes POST and GET requests to api.muapi.ai using curl as a fallback mechanism. This network activity is necessary for the skill's core functionality of processing and generating images.
  • [CREDENTIALS_UNSAFE]: The skill references the MUAPI_API_KEY environment variable. It follows security best practices by instructing the agent to configure this key through standard CLI tools rather than hardcoding credentials.
  • [DATA_EXFILTRATION]: While the skill sends a user-provided image to an external API (api.muapi.ai), this is the primary function of the skill and is not an unauthorized exfiltration of sensitive local data.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 02:04 PM
Security Audit — agent-trust-hub — muapi-chibi-collage-effect