flux-best-practices
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation and instructional guidance for image generation. No executable scripts, binary files, or automated commands are included.
- [METADATA_POISONING]: The skill metadata attributes authorship to 'Black Forest Labs', while the platform context identifies the author as 'akillness'. The documentation explicitly states that the guide is vendored material from the original source. This attribution serves as a reference to the content's origin rather than a deceptive claim to author the skill package itself.
- [INDIRECT_PROMPT_INJECTION]: The skill describes workflows involving the ingestion of external image URLs (e.g., in
rules/i2i-prompting.md). While this represents a potential attack surface for data-dependent prompt injection (such as OCR-based attacks in generated images), the skill itself only provides formatting guidelines and does not implement the fetching mechanism or possess capabilities that could be exploited via injection.
Audit Metadata