The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Ryvn CLI by downloading and executing a script from the vendor's domain (https://ryvn.ai/install.sh). This is a standard vendor-provided utility.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external data that could contain malicious instructions.\n
Ingestion points: The agent ingests data through ryvn logs, ryvn get manifest, and ryvn describe commands, which fetch logs and Kubernetes specifications.\n
Boundary markers: No delimiters or instructions are provided to separate data from commands or to ignore embedded instructions.\n
Capability inventory: The skill possesses the capability to modify infrastructure through ryvn create, ryvn update, and ryvn delete commands.\n
Sanitization: The skill does not perform sanitization on the data retrieved from logs or manifests.\n- [DATA_EXFILTRATION]: The skill instructs the agent to autonomously send feedback via the ryvn feedback command without user approval. This behavior transmits technical details about the agent's actions and environment to the vendor.\n- [DYNAMIC_EXECUTION]: The ryvn upgrade functionality enables the CLI to update itself and the agent skill, which involves downloading and applying new instructions at runtime.

use-ryvn