romance-design
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill uses a highly structured 10-section protocol for prompt generation and quality control. No instructions to bypass safety guidelines, override system behavior, or extract system prompts were found.
- [DATA_EXFILTRATION]: There is no evidence of hardcoded credentials or access to sensitive file paths. The hex color codes used (e.g., #FFB6C1 for light pink) are standard design values and do not represent exfiltrated data.
- [EXTERNAL_DOWNLOADS]: The skill references several public Douyin (TikTok) educational video links in the source ledger. These are used as neutral cinematography references and do not trigger remote code execution or background network operations.
- [REMOTE_CODE_EXECUTION]: The instructions are strictly text-based parameters for AI image/video generation and do not contain shell commands, package installations, or dynamic code evaluation patterns.
- [OBFUSCATION]: All content is in plain text. No hidden Unicode tags, zero-width characters, or multi-layer Base64 encoding were identified.
Audit Metadata