The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the loopnet-pp-cli tool using npx from the @mvanhorn/printing-press-library package on NPM or via go install from the vendor's GitHub repository at github.com/mvanhorn/printing-press-library.
[COMMAND_EXECUTION]: The skill's primary function is to execute the loopnet-pp-cli binary with various subcommands (inventory, sync, caprate, etc.) to process real estate data.
[DATA_EXFILTRATION]: The CLI tool provides an output delivery feature (--deliver webhook:<url>) which allows sending the command output to an external URL. This is a functional feature for data pipelines but represents a pathway for sending data to remote services.
[PROMPT_INJECTION]: The skill ingest data from external sources (LoopNet property descriptions and listings) which could contain adversarial content. This represents a potential indirect prompt injection surface.
Ingestion points: Data enters the agent context via the inventory, property, and sync commands which fetch live content from LoopNet.com.
Boundary markers: None identified in the skill instructions for the ingested data.
Capability inventory: The skill can execute shell commands, write to the local file system (--out), and perform network POST requests (webhook:<url>).
Sanitization: No explicit sanitization of property descriptions or external data is documented in the instructions.

pp-loopnet