The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the execution of shell commands through npx to manage the authentication lifecycle and perform data operations in Google BigQuery.
[EXTERNAL_DOWNLOADS]: The skill fetches the @useclawlink/cli package from the NPM registry to provide the necessary tools for connecting the agent to Google BigQuery.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input by interpolating natural language strings and JSON payloads into CLI command arguments, creating a surface for indirect prompt injection.
Ingestion points: User queries provided to the actions command and JSON data provided to the --input flag in the run command.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are included in the command templates.
Capability inventory: The skill uses shell execution via npx for all operations defined in SKILL.md.
Sanitization: The skill does not describe any specific validation or sanitization mechanisms for the data passed to the CLI tools.

google-bigquery