higgsfield-creative

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates on local project files within the ad-assets/ and experiments/ directories as expected for its stated purpose of ad creation.
  • [EXTERNAL_DOWNLOADS]: Connects to the Higgsfield MCP server at https://mcp.higgsfield.ai/mcp. This is a well-known service for AI media generation.
  • [COMMAND_EXECUTION]: Uses a discovery pattern to find and execute Higgsfield tools based on user intent and available product versions (Soul, Ace, Speak, etc.).
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 10:42 AM
Security Audit — agent-trust-hub — higgsfield-creative