construction-trades-leads
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions to install a Model Context Protocol (MCP) server using the command
claude mcp add --transport http manypi https://mcp.manypi.com/mcp -s user. - [EXTERNAL_DOWNLOADS]: The tool configuration points to an external endpoint at
https://mcp.manypi.com/mcpfor fetching and executing tool functionality. This resource belongs to the skill author's domain. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and process data from external, untrusted sources such as planning registers, accreditation websites, and company project galleries.
- Ingestion points: Data is pulled from external source URLs, project galleries, and hiring pages as specified in the
extra_columnsfield of the ManyPI brief. - Boundary markers: The skill lacks explicit boundary markers or instructions for the agent to ignore potentially malicious content embedded in the retrieved web data.
- Capability inventory: The skill utilizes an MCP tool that facilitates network access and data retrieval across various public registers and websites.
- Sanitization: There is no evidence of sanitization or filtering of the external data before it is processed by the agent.
Audit Metadata