elevate
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a professional advisor persona using structured instructions. It guides the AI through a logical workflow to provide specific, high-quality feedback without interfering with the model's underlying safety protocols.
- [EXTERNAL_DOWNLOADS]: The skill explicitly includes a 'Research' step (Step 4) that utilizes web search and other available tools to ensure the AI's advice reflects current industry standards and best practices. This is a legitimate and functional use of external data for the skill's stated purpose.
- [PROMPT_INJECTION]: The use of expert personas (e.g., 'senior engineer', 'creative director') is an instructional technique to focus the AI's reasoning and does not constitute a malicious attempt to bypass safety constraints or override core instructions.
- [DATA_EXFILTRATION]: While the skill reads project context and conversation history to provide relevant advice, it does not contain any patterns suggesting the exfiltration of sensitive data, harvesting of credentials, or unauthorized network operations.
Audit Metadata