poster-prompt-generator
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and focused on creative prompt engineering. It defines specific design fields (Theme, Style, Color, etc.) to assist in generating structured inputs for image generation models like DALL-E or Midjourney.
- [PROMPT_INJECTION]: While the instructions use strong directives such as 'IMPORTANT' and 'Strictly Prohibited,' these are design-specific constraints intended to ensure variety and quality in output (e.g., preventing repetitive style mapping). They do not attempt to override system safety protocols, extract system prompts, or bypass AI guardrails.
- [DATA_EXFILTRATION]: No network operations, credential harvesting, or access to sensitive file paths were detected. The skill does not perform any outbound communication.
- [REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of external scripts or binaries. The skill operates entirely within the textual conversation context.
- [OBFUSCATION]: The content is written in clear Chinese and English without the use of Base64, zero-width characters, homoglyphs, or other techniques to hide malicious commands.
Audit Metadata