The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @kood/naver-api-cli package from the npm registry using a global installation command. This is an external dependency from a source not specifically identified as trusted.
[COMMAND_EXECUTION]: The skill uses shell commands to interact with the naver-api CLI for search queries and configuration management. This is the intended operational mode for the skill.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from the Naver API HUB search and trend endpoints. It includes a specific instruction to treat API responses as evidence rather than instructions, which serves as a guardrail against potential injection attacks embedded in the external content.
Ingestion points: Naver API search results (e.g., news, blog, images) and Shopping Insight trend data.
Boundary markers: The instruction contract explicitly requires treating API data as evidence rather than instructions.
Capability inventory: The skill can execute shell commands through the CLI and perform global npm package installations.
Sanitization: The workflow specifies using the --json flag for deterministic parsing and structured YAML/JSON files for trend inputs.

naver-api