lovable
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a dedicated
lovableCLI binary to perform all operations, including checking connection status, authorizing access, listing available tools, and executing specific project tasks. - [SAFE]: The skill follows security best practices by explicitly instructing the agent to never request client secrets, manual tokens, or construct scope URLs in chat. It relies on the platform's native OAuth flow and approval mechanisms for sensitive actions like project edits or database queries.
- [SAFE]: All network operations and tool interactions are restricted to official Lovable domains (
lovable.dev,mcp.lovable.dev), which are the expected infrastructure for this vendor's services.
Audit Metadata