The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions to download the Ryvn CLI installation script from the vendor's official domain at https://ryvn.ai/install.sh.\n- [REMOTE_CODE_EXECUTION]: The installation process involves executing a remotely retrieved script via a shell, which is the platform's official setup method.\n- [PROMPT_INJECTION]: The skill processes untrusted data such as application logs and Kubernetes manifests, which creates a surface for indirect prompt injection where malicious content in the data could attempt to influence agent actions.\n
Ingestion points: Application logs and system manifests retrieved via the ryvn logs and ryvn get manifest commands (documented in references/operate.md).\n
Boundary markers: Absent. The skill does not define specific delimiters or instructions to ignore embedded commands within the log or manifest output.\n
Capability inventory: The skill has high-privilege capabilities including environment provisioning, service deployment, configuration management, and task approval via the ryvn CLI tool.\n
Sanitization: None specified. There is no evidence of filtering or validation of the retrieved log or manifest content before processing by the agent.\n- [COMMAND_EXECUTION]: The skill makes extensive use of the ryvn CLI to perform all infrastructure, deployment, and operational tasks.

use-ryvn