Recommend

Context-aware recommendations. Learns preferences, researches options, anticipates expectations.

This skill appears coherent and does what it claims, but it will read your conversation history and memory files and write preference updates there. Before installing, review your memory (memory/*.md, MEMORY.md) for any sensitive items you don't want a recommendation skill to read or store (API keys, passwords, private notes). If you prefer, disable autonomous invocation for the agent or configure the agent's memory policies so the skill only stores non-sensitive preference signals. Finally, ask how the skill performs external research (which sites/APIs it uses) if you want tighter network/privacy controls.

Type: OpenClaw Skill Name: recommend Version: 1.0.0 The OpenClaw skill bundle for 'recommend' is benign. All files (SKILL.md, categories.md, sources.md, _meta.json) define a standard recommendation process, instructing the AI agent to gather context from its own memory files and conversation history, extract preferences, research options, and store learnings back into memory. There are no instructions for data exfiltration, unauthorized execution, persistence, or any form of prompt injection aiming to subvert the agent's purpose or access sensitive data beyond its operational scope. The instructions are clear and directly support the stated goal of providing context-aware recommendations.