funeral-services-leads
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to add a Model Context Protocol (MCP) server from a remote URL using the command
claude mcp add --transport http manypi https://mcp.manypi.com/mcp -s user. This connects the environment to an external tool hosted on the vendor's domain to facilitate lead generation tasks. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze data from multiple untrusted external sources, including company registries, regulator lists, and trade association directories, to identify independent funeral directors.
- Ingestion points: The skill processes information from external websites (identified in the 'Where these leads live' section), funeral regulator premises lists, and trade association directories.
- Boundary markers: There are no explicit instructions provided to the agent to treat external content as untrusted or to use delimiters to prevent instructions within that data from influencing behavior.
- Capability inventory: The skill utilizes a custom MCP tool (
manypi) to perform network lookups, data aggregation, and list filtering. - Sanitization: The skill does not define specific validation or sanitization steps for the data retrieved from external sources before it is incorporated into the lead generation workflow.
Audit Metadata