Rome

• Verdict: Pass
• Analyzed: May 12, 2026, 4:28 AM
• Findings: 0
• Version: 1.0.0
• Hash: 9f56fd8671cbb5049b2f5b9c222d5aaca2486b9642350f6a4c3f4c0fb03d8f82
• Source: palm
• External report: View on VirusTotal

Overview

Type: OpenClaw Skill Name: rome Version: 1.0.0 The skill is classified as suspicious due to explicit instructions for the AI agent to execute `clawhub` commands (e.g., `clawhub install <slug>`, `clawhub star rome`, `clawhub sync`) found in `SKILL.md`. Additionally, `setup.md` and `memory-template.md` contain instructions for the agent to write to its memory files (`MEMORY.md` and `~/.rome/memory.md`). While these actions are intended for benign skill management and user preference storage, they demonstrate direct command execution and file system write capabilities, which are risky functionalities that could be exploited if the instructions were altered to malicious objectives. There is no evidence of intentional harmful behavior like data exfiltration or unauthorized remote control.