The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill instructs the installation of external binaries using npx -y @mvanhorn/printing-press-library and go install github.com/mvanhorn/printing-press-library/.... These commands fetch and execute code from remote repositories associated with the vendor 'mvanhorn'.
[COMMAND_EXECUTION]: The skill makes extensive use of the Bash tool to execute administrative and management commands via the godaddy-pp-cli binary. It also executes installation scripts through npx and the go compiler.
[DATA_EXFILTRATION]: The CLI supports an output delivery feature (--deliver webhook:<url>) that allows the results of any command—which may include sensitive account details, domain configurations, or abuse ticket information—to be automatically POSTed to an external URL.
[CREDENTIALS_UNSAFE]: The documentation provides instructions for managing sensitive GoDaddy API keys and secrets by exporting them as environment variables (GODADDY_API_KEY, GODADDY_API_SECRET) or storing them in a local configuration file (~/.config/godaddy-pp-cli/config.toml).
[INDIRECT_PROMPT_INJECTION]: The skill has a large attack surface as it ingests data from external GoDaddy API endpoints (abuse tickets, certificates, domain listings) and returns this content to the agent context.
Ingestion points: Data retrieved via abuse, domains, certificates, and agents command groups in SKILL.md.
Boundary markers: None identified; external API data is returned directly to the agent's context.
Capability inventory: The skill possesses high-privilege capabilities via the Bash tool to execute local commands and network requests.
Sanitization: No filtering or sanitization of API-returned content is mentioned before it is processed by the agent.
[PERSISTENCE]: The skill provides instructions for registering an MCP server using claude mcp add, which configures the binary to be loaded automatically in future agent sessions.

pp-godaddy