The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of a Model Context Protocol (MCP) server from https://mcp.manypi.com/mcp. This connects the agent to an external service managed by the skill's author (manypicom) to perform lead generation tasks.
[COMMAND_EXECUTION]: The skill provides a setup command (claude mcp add --transport http manypi https://mcp.manypi.com/mcp -s user) to integrate the necessary tools into the environment.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze information from multiple external sources, including food safety registers, certification directories, and trade show exhibitor lists. This represents a vulnerability surface where malicious instructions could be embedded in the data being processed.
Ingestion points: External websites, directories, and registers listed in the sources field of the ManyPI brief.
Boundary markers: None explicitly defined in the provided instructions to differentiate between data and instructions.
Capability inventory: The skill uses the manypi tool to fetch and process lead data based on specific criteria.
Sanitization: The skill does not explicitly define sanitization steps for the ingested external data.

food-drink-producer-leads