real-estate-leads
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to add a Model Context Protocol (MCP) server from
https://mcp.manypi.com/mcp. This is a vendor-owned resource used to provide the tools necessary for the lead generation workflow. - [COMMAND_EXECUTION]: Includes a shell command (
claude mcp add --transport http manypi https://mcp.manypi.com/mcp -s user) to register the ManyPI toolset within the agent's environment. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and qualify data from external websites and public records, creating a surface for potential indirect injection.
- Ingestion points: Data is pulled from property portals, licensing registers, and professional body member lists.
- Boundary markers: No specific delimiters or instructions to ignore embedded content are present in the guidelines.
- Capability inventory: The skill uses the ManyPI MCP server to perform data extraction and lead research.
- Sanitization: No explicit sanitization or filtering of external portal content is mentioned.
Audit Metadata