The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external content such as research papers and project feeds.
Ingestion points: Content retrieved via pz paper and pz feed commands from the Paperzilla API.
Boundary markers: No explicit delimiters or boundary instructions are defined to separate untrusted paper content from agent instructions.
Capability inventory: The agent can execute shell commands via the pz CLI and submit feedback to external APIs.
Sanitization: No specific sanitization or validation steps are outlined for the retrieved markdown or JSON data before the agent summarizes it.
[EXTERNAL_DOWNLOADS]: The skill provides instructions to install and update the pz CLI tool from official Paperzilla repositories and domains.
Downloads the CLI using Homebrew (paperzilla-ai/tap/pz), Scoop (github.com/paperzilla-ai/scoop-bucket), or direct download from paperzilla.ai.
This behavior is standard for the tool's intended use and follows official vendor distribution channels.
[COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands using the pz binary.
Commands include project listing, feed retrieval, and paper downloads.
These operations are restricted to the functionality of the Paperzilla CLI tool.

paperzilla