The Agent Skills Directory

[SAFE]: The skill operates as intended for a design tool, using local markdown references (references/platform-specs.md) to determine platform-appropriate dimensions and guidelines.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for untrusted data as it processes user-supplied topics, messages, and brand guidelines to generate visual assets. However, the risk is minimal as the capabilities are limited to image generation and brand checking.
Ingestion points: User-provided topics, messages, brand elements, and reference images described in the Standard Workflow.
Boundary markers: None explicitly defined in the instructions.
Capability inventory: Invokes creator-stack:nanobanana for image generation and creator-stack:brand-guidelines for validation.
Sanitization: No explicit sanitization or escaping of user-provided text is mentioned before interpolation into image generation prompts.

social-graphic