The Agent Skills Directory

[SAFE]: The skill operates using local reference files to construct image generation prompts. It explicitly prohibits the use of external image providers (like OpenAI or Gemini APIs) and forbids the agent from requesting API keys, adhering to a secure-by-default posture.
[SAFE]: No malicious patterns such as prompt injection, obfuscation, or unauthorized data exfiltration were detected. File access is limited to the skill's own reference directory and standard temporary paths for prompt assembly.
[SAFE]: The provided pseudo-code and templates are for informational purposes to guide the agent's internal logic and do not involve the execution of untrusted external scripts.

image-studio