media-higgsfield-core
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a purely informational core that provides schemas and protocols for Higgsfield MCP image and video generation.
- [SAFE]: It promotes robust design by instructing consumer skills to use live tool calls (
models_explore) instead of hardcoding parameters, which reduces the risk of model drift or invalid configurations. - [EXTERNAL_DOWNLOADS]: References official documentation and guidelines from well-known technology organizations (Higgsfield AI, Google, OpenAI, Black Forest Labs, Alibaba). These references are used solely for prompt engineering and model capability research and do not involve remote code execution.
- [SAFE]: Implements input constraints by requiring media to be converted to internal IDs (
media_idorjob_id) rather than accepting raw external URLs directly in generation tools. - [SAFE]: No obfuscation, data exfiltration, or persistence mechanisms were detected. The skill focuses on job lifecycles, cost preflights, and prompt craft rules.
Audit Metadata