The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill downloads and executes the google-agents-cli package via the uvx package runner and adds the skill using npx. These actions facilitate the setup of official development tools.
[COMMAND_EXECUTION]: Employs bash commands to perform core development lifecycle tasks, including project scaffolding, dependency installation, agent execution, and deployment to Google Cloud services such as Agent Runtime, Cloud Run, and GKE.
[INDIRECT_PROMPT_INJECTION]: The skill processes natural language data which serves as a potential vector for indirect prompt injection. Untrusted content could potentially influence the agent's behavior during execution or evaluation.
Ingestion points: Ingests natural language prompts via the agents-cli run command and processes test data from files within the evals/ directory.
Boundary markers: The instructions do not specify the use of delimiters or protective instructions to distinguish between data and commands within the processed input.
Capability inventory: The environment provides capabilities for file system modification, network-based deployments, and command execution through the Bash tool.
Sanitization: There is no mention of sanitization, filtering, or validation steps for the inputs processed by the agent.

agents-cli