The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the apartments-pp-cli and apartments-pp-mcp binaries from the author's GitHub repository (github.com/mvanhorn/printing-press-library) and an NPM package (@mvanhorn/printing-press).
[REMOTE_CODE_EXECUTION]: Executes code downloaded from remote repositories via go install and npx, and subsequently runs the installed binary to perform tasks.
[COMMAND_EXECUTION]: The skill's primary mode of operation is generating and executing shell commands to interact with the local CLI tool for searching and analyzing listings.
[DATA_EXFILTRATION]: Includes a functional capability (--deliver webhook:<url>) that allows the agent to send command outputs (which may include listing data or search results) to an arbitrary external URL.
[PROMPT_INJECTION]: Presents a surface for indirect prompt injection (Category 8) due to the following factors:
- Ingestion points: Processes untrusted HTML data from external listing pages via the listing and rentals commands (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore embedded content are present in the prompt templates.
- Capability inventory: The skill can execute subprocesses, write to files, and perform network POST requests via webhooks.
- Sanitization: No documentation of sanitization or filtering of the external listing data is provided.

pp-apartments