flux-best-practices
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill is composed exclusively of Markdown files providing instructions and examples for prompting image generation models. No scripts (.py, .js, .sh), configuration files, or binaries were found that could execute on the host system.
- [SAFE]: The skill contains references to official documentation domains (bfl.ai) and illustrative examples (example.com). There are no hardcoded credentials, network exfiltration attempts, or prompt injection patterns detected. The 'Impact' levels mentioned in the documentation refer to the importance of prompting techniques for image quality, not security severity. The authorship metadata attributing the content to Black Forest Labs is consistent with the described 'vendored' nature of the guide.
Audit Metadata