The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill downloads its CLI and MCP binaries from the vendor's official repositories on GitHub and NPM (@mvanhorn/printing-press-library). These downloads originate from the infrastructure of the author provided in the context.- [COMMAND_EXECUTION]: The skill instructs the agent to execute the goodreads-pp-cli binary to interact with Goodreads services.- [DATA_EXFILTRATION]: The CLI includes a --deliver webhook:<url> feature that can send command output to arbitrary external URLs. This is a functional feature for data delivery and is documented as such.- [CREDENTIALS_UNSAFE]: Authentication requires session cookies and JWT tokens provided via environment variables. The skill avoids hardcoding secrets and suggests standard configuration paths.- [PROMPT_INJECTION]: The skill processes untrusted data from Goodreads (feed, reviews, books) which represents a surface for indirect prompt injections.
Ingestion points: Data enters via commands like feed list and review get in SKILL.md.
Boundary markers: None identified in the skill instructions.
Capability inventory: Shell command execution via goodreads-pp-cli and network operations.
Sanitization: No specific sanitization steps are documented for external data processing.

pp-goodreads