The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to install an external binary (ankiweb-pp-cli) using npx or go install from the vendor's GitHub repository (github.com/mvanhorn/printing-press-library). These resources are managed by the skill's vendor.
[COMMAND_EXECUTION]: The skill executes shell commands by passing user-supplied arguments directly to the ankiweb-pp-cli binary. This is the primary method of interaction for the skill's functionality.
[CREDENTIALS_UNSAFE]: The tool requires and manages sensitive session cookies (ANKIWEB_COOKIES) for features that access user-specific cloud-synced decks and study statistics. It provides mechanisms to import these cookies from local browser profiles.
[DATA_EXFILTRATION]: The CLI tool supports a --deliver webhook:<url> feature. This allows the output of any command (including sensitive deck lists or card data) to be sent via an HTTP POST request to a user-specified URL. While a functional feature, it represents a significant exfiltration surface if misused.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources (AnkiWeb shared decks) and displays it in the terminal. Maliciously crafted deck titles or metadata could potentially influence the agent's behavior if processed without strict boundary markers.

pp-ankiweb