architecture-design-firm-leads
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to add an MCP (Model Context Protocol) server via
https://mcp.manypi.com/mcp. This connects the agent to an external service for processing lead generation data. The domain belongs to the skill's authoring organization. - [COMMAND_EXECUTION]: The skill provides a
bashcommand to configure the agent environment:claude mcp add --transport http manypi https://mcp.manypi.com/mcp -s user. This command is used to install the necessary tool for the skill's primary function. - [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves ingesting data from external sources which could potentially contain malicious instructions.
- Ingestion points: Architecture practice websites, team pages, planning application records, and professional registers (described in
SKILL.md). - Boundary markers: None specified in the instructions to prevent the agent from following instructions found in external data.
- Capability inventory: The skill utilizes the ManyPI MCP server to search and retrieve data from the web.
- Sanitization: No explicit sanitization or filtering steps are defined for the data retrieved from external sources.
Audit Metadata