The Agent Skills Directory

[SAFE]: The skill operates as a prompt engineering framework. It instructs the agent to read local reference files and generate prompts for image models.
[EXTERNAL_DOWNLOADS]: The references/cases.md file contains links to goodcase.ai and x.com. These are used for documentation and visual reference purposes and are treated as safe within the context of the skill's creative purpose.
[COMMAND_EXECUTION]: No shell commands, script execution, or system-level operations were detected.
[DATA_EXFILTRATION]: No sensitive file access or network exfiltration patterns were found.
[PROMPT_INJECTION]: The skill contains no instructions to bypass safety filters or override system instructions. It includes healthy safety and attribution guidelines to prevent impersonation and ensure source attribution.
[INDIRECT_PROMPT_INJECTION]: While the skill processes user inputs for image generation (subject, audience, etc.), the risk is inherently low as the output is a text prompt for an image generator, and the skill includes specific 'Preserve / Replace / Avoid' gates to maintain structure.

photo-reinterpretation-diptych-by-1ukcvvc