franchise-expansion-leads
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides a command to add a Model Context Protocol (MCP) server from
https://mcp.manypi.com/mcp. This URL belongs to the skill's author, manypicom, and is used to extend the agent's capabilities with the vendor's lead generation tools. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize untrusted data from external sources such as franchise disclosure documents and recruitment portals.
- Ingestion points: Data is gathered from franchisor location finders, association directories, disclosure documents, and recruitment portals as specified in the
sourcesfield of the ManyPI brief. - Boundary markers: None are defined to differentiate between instructions and data retrieved from external documents.
- Capability inventory: The skill uses the
manypiMCP tool to query these sources and extract specific details like mandated suppliers and unit counts. - Sanitization: The skill does not explicitly mention any sanitization or filtering of the content retrieved from these external documents.
Audit Metadata