flux
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external files such as brand-profile and design-and-templates to ensure consistency in generated images. It lacks explicit boundary markers or instructions to isolate data from instructions, which creates a surface for indirect prompt injection if those external files contain malicious directives. The agent has the capability to call image generation and editing APIs based on this combined context.
- Ingestion points: The skill reads brand-profile and design-and-templates files as part of its initialization (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the documentation for handling these external data sources.
- Capability inventory: The agent is authorized to call image generation and editing APIs programmatically where connected (e.g., BFL, fal, Replicate, Together) (SKILL.md, references/scope-and-connections.md).
- Sanitization: There are no specified sanitization or validation steps for content retrieved from external sources before it is interpolated into model prompts.
Audit Metadata