The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the @ideal-postcodes/cli package from the official NPM registry, which is a verified resource provided by the author.
[COMMAND_EXECUTION]: Core functionality is delivered through the execution of the idpc CLI tool. This includes sensitive operations such as credential management and API configuration, which are performed via subprocess calls to the binary.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface as it processes external address data that could contain malicious instructions.
Ingestion points: External data is ingested through address queries, file imports, and standard input streams (observed in SKILL.md, references/cleanse.md, and references/find.md).
Boundary markers: The instructions lack explicit delimiters or headers to differentiate untrusted address data from agent instructions.
Capability inventory: The skill uses subprocess calls to execute the idpc command-line utility across all reference scripts.
Sanitization: No validation or escaping mechanisms are described for sanitizing the output of the CLI before it is presented to the agent context.

idpc-cli