emotion-metaphor-image-prompting
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed of markdown and YAML documentation that defines a prompt engineering workflow. It does not contain executable scripts, shell commands, or network operations.
- [DATA_EXFILTRATION]: There is no logic present that accesses sensitive user data, system environment variables, or local files. The skill operates entirely on user-provided descriptions of emotions.
- [EXTERNAL_DOWNLOADS]: No remote URLs, packages, or external resources are fetched or executed. All referenced templates and examples are local to the skill directory.
- [PROMPT_INJECTION]: The skill does not contain instructions aimed at bypassing AI safety filters or overriding system behaviors. The prompting templates include explicit negative constraints (e.g., 'no gore', 'no brutality') to ensure generated content remains metaphorical and within safety guidelines.
- [COMMAND_EXECUTION]: No shell commands or subprocess calls are present in the analyzed files.
Audit Metadata