The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches the judgeme-pp-cli binary using npx from the @mvanhorn/printing-press-library package on NPM and via go install from the author's GitHub repository (github.com/mvanhorn/printing-press-library). These resources are owned by the skill's vendor and represent standard installation procedures for this tool.
[COMMAND_EXECUTION]: The skill utilizes the judgeme-pp-cli tool to perform review management and storefront operations. It includes a --deliver webhook feature that permits the agent to route command output (which may contain sensitive review or shop data) to arbitrary external URLs.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to its interaction with external review data.
Ingestion points: The skill reads raw, third-party review content from Judge.me via the sync, reviews index, and reviews get commands.
Boundary markers: No boundary markers or 'ignore' instructions are used when passing this data to the agent context.
Capability inventory: The skill has access to Read Bash tools, file system writes via the --deliver file flag, and network exfiltration via the --deliver webhook flag.
Sanitization: The skill documentation explicitly warns that raw review information is not sanitized and may contain malicious content.

pp-judgeme