The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the openipa-pp-cli binary using npx from the @mvanhorn/printing-press-library package or via go install from the vendor's GitHub repository.- [DATA_EXFILTRATION]: The CLI tool includes a --deliver webhook:<url> flag, which allows the agent to send command results directly to an external URL. This creates a mechanism for potential data exfiltration if directed to use an untrusted endpoint.- [DATA_EXFILTRATION]: The skill documents a feedback command that can transmit local notes to a remote server if the OPENIPA_FEEDBACK_ENDPOINT environment variable is set.- [COMMAND_EXECUTION]: The skill relies on executing various shell commands to install the CLI, verify its version, and perform administrative queries.- [PROMPT_INJECTION]: Indirect injection risk exists as the skill processes data from the Italian Public Administration Index (IPA).
Ingestion points: Data retrieved via openipa-pp-cli commands (e.g., entity names, descriptions).
Boundary markers: None specified in the instructions to delimit untrusted data.
Capability inventory: Shell command execution, network requests via the CLI, and file writing capabilities.
Sanitization: No explicit sanitization or escaping of the external API data is described before processing by the agent.

pp-openipa