Tarot from Univoice

• Verdict: Pass
• Analyzed: May 12, 2026, 4:28 AM
• Findings: 0
• Version: 1.0.0
• Hash: f030c49c040d0039b4ad90f12654dc5b383c4e74f05ffd5dbe02007754a129e5
• Source: palm
• External report: View on VirusTotal

Overview

Type: OpenClaw Skill Name: tarot Version: 1.0.0 The skill bundle contains a `_meta.json` file and a `SKILL.md` file. The `SKILL.md` provides detailed instructions for an AI agent to perform a reflective tarot reading. It explicitly defines ethical boundaries, avoids harmful language, and instructs the agent to 'Randomly select cards internally', preventing external calls or data exfiltration. There are no instructions for malicious execution, data exfiltration, persistence, or prompt injection designed to subvert the agent for harmful purposes. The instructions are clearly aligned with the stated purpose and lack high-risk behaviors.