midjourney-replicate-flux
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily instructional, providing templates and aesthetic guides for prompt engineering. No malicious patterns or bypass attempts were detected.
- [COMMAND_EXECUTION]: The skill utilizes the
mcp__replicate__create_predictionstool to interface with Replicate's API for image generation. This is an intended functionality performed through an established MCP server. - [REMOTE_CODE_EXECUTION]: The skill includes a specific warning against generating or executing custom scripts, directing the agent to use only the pre-installed MCP tool, which significantly reduces the attack surface for unauthorized code execution.
- [EXTERNAL_DOWNLOADS]: References official documentation for the FLUX model on Replicate. These references are documented neutrally as they point to well-known service providers and serve to guide the user on model parameters.
Audit Metadata