The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of an external Model Context Protocol (MCP) server from https://mcp.manypi.com/mcp. This URL belongs to the skill's authoring organization and is used to provide the lead generation functionality.
[COMMAND_EXECUTION]: Provides a command to register the MCP tool within the agent environment: claude mcp add --transport http manypi https://mcp.manypi.com/mcp -s user.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it is designed to ingest and process data from external B2B SaaS websites, review platforms, and job boards.
Ingestion points: External data sources including company websites, VC portfolios, job boards, and review platforms as defined in the sources field of the ManyPI brief.
Boundary markers: The skill uses a structured JSON brief to define search parameters, but lacks explicit boundary markers or instructions for the agent to ignore malicious patterns embedded within the scraped website content.
Capability inventory: The skill adds a custom tool (manypi) that likely performs network operations and data retrieval. It also instructs the agent to analyze homepage content, job posts, and help documentation.
Sanitization: There is no evidence of sanitization or filtering logic for the content retrieved from external sources before it is processed by the agent.

saas-b2b-leads