The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (such as address strings, email lists, and phone numbers) from files or standard input, which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Address strings, email lists, and phone numbers are ingested via idpc cleanse, idpc email, and idpc phone commands using the --file or --stdin flags. Configuration updates are ingested via idpc keys update --json-body.
Boundary markers: The instructions do not define specific delimiters or guidelines for the agent to ignore instructions embedded within the processed data.
Capability inventory: The skill executes idpc CLI subcommands to perform network API calls to vendor endpoints and file writing operations (CSV/JSON output).
Sanitization: No sanitization or validation steps are defined in the instructions for the external content before it is passed to the CLI tool.
[COMMAND_EXECUTION]: The skill instructions involve executing the idpc command-line interface to interact with the Ideal Postcodes API and manage account configurations.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @ideal-postcodes/cli package from the NPM registry. This is a resource provided by the skill's author for the intended functionality of the skill.

ideal-postcodes-cli