frame-liquid-bg-hero
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No attempts to override safety guidelines, bypass constraints, or extract system prompts were detected.
- [DATA_EXFILTRATION]: No sensitive file paths are accessed, and no unauthorized network operations are performed. The skill uses defined MCP tools for its core logic.
- [REMOTE_CODE_EXECUTION]: The skill does not perform any remote script execution or unverified package installations.
- [OBFUSCATION]: No hidden, encoded, or obfuscated content (e.g., Base64, zero-width characters, or homoglyphs) was found.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes user input to create a design brief, it lacks dangerous capabilities or automated exfiltration paths that would elevate the risk of indirect injection.
Audit Metadata