OpenClaw CLI

• Analyzed: May 12, 2026, 4:26 AM
• Findings: 1
• Version: 1.0.0
• Hash: d7abc855c2758660eb593f24c75cf17d5d6437005568925867a5aca6119532fe
• Source: palm
• External report: View on VirusTotal

Findings (1)

The OpenClaw CLI skill is designed to operate and troubleshoot the `openclaw` command-line interface. The `SKILL.md` and `references/command-map.md` files contain explicit safety rules, such as requiring user confirmation before executing destructive commands (`reset`, `uninstall`, `--force`) and prioritizing non-destructive diagnostics. While the `openclaw` CLI itself may possess powerful capabilities (e.g., `cron`, `sandbox`), the skill's instructions to the AI agent consistently emphasize safe usage and user consent, with no evidence of prompt injection for malicious intent, data exfiltration, or unauthorized actions. The installation instructions in `README.md` are for the user, not for the agent to execute.