The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external public planning records and local authority portals. This introduces a surface for indirect prompt injection if the records contain malicious text designed to influence the agent.
Ingestion points: Local authority planning portals, national planning data aggregators, building control approval records, commencement notices, environmental and discharge permits, construction project databases. (File: SKILL.md)
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified for the ingested data.
Capability inventory: The skill facilitates data extraction and contact identification, leveraging the agent's reasoning and retrieval capabilities. No direct shell or file-write capabilities are explicitly declared in this file.
Sanitization: The skill does not describe specific sanitization or filtering techniques for the content retrieved from external planning portals.
[EXTERNAL_DOWNLOADS]: The skill instructs the user to add a remote Model Context Protocol (MCP) server provided by the vendor.
Evidence: The command claude mcp add --transport http manypi https://mcp.manypi.com/mcp -s user adds a tool server hosted at https://mcp.manypi.com/mcp. (File: SKILL.md)

planning-permission-leads