Rotifer Agent

End-to-end guide for building AI Agents from Genes: intent decomposition, Gene selection, Genome composition, Agent creation, and testing. Use when the user...

This is an authoritative guide for using the Rotifer CLI to design and run agents and appears internally consistent. Before following commands: (1) be aware that running the suggested npx commands will download and execute code from the npm registry — verify package names, versions, and the upstream rotifer.dev / repository to ensure you trust them; (2) the workflow expects you to inspect and edit local .rotifer JSON files — review those edits carefully before running agents; (3) the guide may route you to other skills (e.g., gene-dev) — confirm those skills' trustworthiness if they are invoked; (4) no credentials are required by this skill itself, but avoid pasting secrets into agent configs you create unless necessary and understood.

Type: OpenClaw Skill Name: rotifer-agent Version: 1.0.3 The skill provides a framework for an AI agent to build and execute code pipelines using the Rotifer CLI, involving high-risk operations such as shell command execution and remote package installation (e.g., 'npx @rotifer/playground' and 'rotifer install' in SKILL.md). While these capabilities are aligned with the stated purpose of agent development, the instructions lack any guidance for input sanitization when the AI constructs shell commands from user-provided strings (e.g., agent names or input data), creating a significant shell injection vulnerability. The reliance on fetching and executing remote artifacts from the @rotifer npm scope and a cloud registry further increases the risk profile.