The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run a specialized server (yandex-metrika-mcp-server) using npx to interact with the API.
[EXTERNAL_DOWNLOADS]: The instructions prompt the agent to use npx -y, which downloads and executes the server package from the NPM registry at runtime.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from the Yandex Metrika API, which is an external source and could potentially contain malicious content.
Ingestion points: API responses returned by the call command in SKILL.md.
Boundary markers: The agent is instructed to distinguish between the data and _meta keys in the JSON response.
Capability inventory: The skill can execute shell commands via npx and access Yandex API endpoints over the network.
Sanitization: The server implementation includes logic to truncate long responses and scrub sensitive tokens from metadata URLs.

yandex-metrika