The Agent Skills Directory

[SAFE]: The skill is entirely instructional and does not involve scripts, command execution, or external network operations. It defines a workflow for creating consistent visual assets.
[INDIRECT_PROMPT_INJECTION]: The skill ingests user descriptions to generate environment plates and spatial locks. While it lacks explicit boundary markers for untrusted input, the skill does not utilize any high-risk capabilities (such as file writing, shell execution, or network exfiltration) that would allow for exploitation via prompt injection.

environment-scene