The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install a CLI tool using npx -y @mvanhorn/printing-press and go install github.com/mvanhorn/printing-press-library/.... These sources are associated with the vendor context provided for this skill.
[COMMAND_EXECUTION]: The skill's primary operation involves executing the render-pp-cli binary through shell commands to perform analytics and management tasks on Render services.
[DATA_EXFILTRATION]: The skill documents a --deliver webhook:<url> feature that allows the output of any command to be POSTed to a remote URL. This capability can be used to send sensitive infrastructure metadata, audit logs, and service configurations to external endpoints. Additionally, the feedback command can transmit data to a configurable RENDER_FEEDBACK_ENDPOINT.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The skill retrieves and processes external data from the Render API, including logs (render-pp-cli logs), audit entries (render-pp-cli audit search), and service events.
Boundary markers: The skill encourages the use of the --agent flag, which outputs data in structured JSON format, providing some structural separation between data and instructions.
Capability inventory: The skill has shell execution capabilities via the render-pp-cli and can perform network operations via the webhook delivery mechanism.
Sanitization: There is no explicit documentation of sanitization or filtering of the content retrieved from the Render API before it is presented to the agent's context.

pp-render