muapi-amazon-product-listing

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: Potential for indirect prompt injection due to unsanitized input interpolation. User-provided data from fields such as product_name, product_category, and key_features is directly inserted into prompt strings for various image models (e.g., gpt4o-text-to-image, nano-banana-pro). The lack of boundary markers or escaping logic means malicious input could potentially manipulate the output or behavior of the image generation service.
  • [COMMAND_EXECUTION]: Orchestration of vendor CLI and API calls. The skill instructions direct the agent to use the muapi CLI tool and curl commands to interact with api.muapi.ai. These operations use the MUAPI_API_KEY environment variable for authentication and are consistent with the skill's stated purpose of utilizing the author's platform for image generation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 02:05 PM
Security Audit — agent-trust-hub — muapi-amazon-product-listing