what-would-lenny-do
Pass
Audited by Gen Agent Trust Hub on Jul 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill follows best practices for Retrieval-Augmented Generation (RAG) by defining a multi-phase process for searching and selecting content.
- [SAFE]: The skill uses a scoped MCP server (
lennysdata) and its associated tools for data retrieval, which limits the scope of operations to defined content searches and reads. - [SAFE]: No evidence of prompt injection or attempts to bypass safety filters. The instructions are focused on guiding the agent's behavior for its intended personas and tasks.
- [SAFE]: No hardcoded credentials or unauthorized network operations. The network communication is handled through the MCP server interface, which is a standard execution pattern.
Audit Metadata