The Agent Skills Directory

[SAFE]: The skill acts as a wrapper for the Higgsfield MCP, facilitating image generation requests through official tool calls. The integration points with higgsfield.ai are transparent and consistent with the skill's stated purpose.- [SAFE]: No evidence of prompt injection, data exfiltration, or malicious persistence was found. The skill focuses solely on its stated purpose of AI image generation, using standard tool execution patterns.- [SAFE]: External references are limited to the official documentation and API endpoints of the service provider, adhering to standard integration practices for AI-enabled services.- [SAFE]: The skill ingests user input to construct image prompts. While this represents a potential surface for indirect prompt injection, the impact is confined to image generation, and the documentation notes the presence of provider-level NSFW and content filtering.

higgsfield-image