The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the installation of a Model Context Protocol (MCP) server using the command: claude mcp add --transport http manypi https://mcp.manypi.com/mcp -s user. This persists a remote tool in the agent's environment.
[EXTERNAL_DOWNLOADS]: The skill fetches tool configuration and execution logic from the vendor-controlled domain mcp.manypi.com during the MCP installation process.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, untrusted sources which could contain malicious instructions.
Ingestion points: Public job boards, recruitment aggregators, member directories, and company filings (SKILL.md).
Boundary markers: None present; the instructions do not specify delimiters or safety warnings for the ingested data.
Capability inventory: The agent uses the manypi tool and potentially browser-based search capabilities to retrieve and process external records.
Sanitization: There are no instructions for sanitizing or validating the content retrieved from external job postings or directories.

recruitment-agency-leads