higgsfield
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for the user to integrate an external Model Context Protocol (MCP) server from
https://mcp.higgsfield.ai/mcp. This is a necessary and standard configuration for connecting the agent to the Higgsfield generation service. - [SAFE]: The skill implements a mandatory 'cost approval rule' that requires the agent to verify credit balances and obtain explicit user confirmation ('go', 'yes', 'fire') before performing any generation tasks. This provides significant protection against accidental or silent credit burn.
- [SAFE]: Analysis of the skill instructions and setup commands found no evidence of prompt injection, data exfiltration, obfuscation, or unauthorized privilege escalation.
Audit Metadata