The Agent Skills Directory

[SAFE]: The skill provides legitimate instructions for prompt engineering related to character consistency in image generation.
[PROMPT_INJECTION]: No evidence of prompt injection, jailbreak attempts, or instructions to ignore safety guidelines were found. The language is purely instructional and focused on the intended task.
[DATA_EXFILTRATION]: No sensitive file access, network requests to external domains, or hardcoded credentials were detected.
[EXTERNAL_DOWNLOADS]: There are no commands or instructions that download or execute external code or scripts.
[COMMAND_EXECUTION]: The skill uses a specific tool save_character_final_prompt to handle its output, which is a standard pattern for agent capabilities and does not involve arbitrary command execution.

character-prompt