RamaLama CLI

Run and interact with AI agents.

This skill appears to do what it says: it expects a local 'ramalama' binary and (optionally) a container runtime and documents how to use them. Before installing/use: (1) verify the source of the ramalama package (brew tap or the 'uv' formula) to ensure you trust the distributor; (2) be mindful that running 'serve' exposes an HTTP API — protect it with network controls or auth if you will serve sensitive data; (3) model pulls will download potentially large files and use significant CPU/GPU/memory and network bandwidth; (4) when running in containers, ensure images and mounts are trusted and avoid mounting sensitive host paths into model containers. If you need higher assurance, ask the publisher for a canonical homepage/repository or an official release URL for the ramalama binary before installing.

Type: OpenClaw Skill Name: ramalama-cli Version: 1.0.0 The skill bundle is classified as benign. It provides instructions and documentation for using the 'ramalama' CLI tool, which is designed for running and interacting with AI agents. All commands and instructions in `SKILL.md` and `references/models.md` are directly related to the stated purpose, including installing the tool, running AI models, serving endpoints, and troubleshooting. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, prompt injection attempts designed to subvert the agent's purpose, or obfuscation. While the skill involves powerful capabilities like shell execution and network access (e.g., `ramalama pull`, `curl localhost`, `podman logs`), these are transparently presented and are integral to the legitimate function of the 'ramalama' tool.